Dimension reduction (DRs) are significant in data analysis to reduce the complexity of high dimensional data while preserving information to the greatest extent. However, the complex processes involved in DRs attribute to their inability to reason the relationship between the projection and the original data features (dimensions). "Why points are clustered?" and "What feature/s caused the points to scatter?" are some of the common questions. As a solution, we use gradients of the projection to generate visual explanations of the DRs. Utilizing these gradients, we show the point-wise sensitivities of the projection with respect to the original data features to explain the reasoning of DR. The combination of the gra- dients with various visualization techniques contribute to the exploration of the impact of dimensions on the projection. To overcome the curse of dimensionality, we propose inter- active techniques that facilitate the combination and comparison of features impact on the projection through gradients. Encapsulating the gradients and the visualization techniques, we present a web-based framework that facilitates an overview of impacts of all features and allows users to selectively explore notable features. / Master of Science / Data is prevalent in almost every facets of our lives. A simple data may comprise a few rows and couple of columns. Such data can be easily visualized and understood through simple visualization tools such as charts and graphs. However the real world data consists of large number of rows and columns (features, dimensions). As the number of features increase, so does the complexity to visualize and understand the data. One of the methods to reduce the high dimension data to low dimension is the dimension reduction (DR). DR methods generate a simpler form of data usually in 2D format which can be easily understood by human eyes. Even though the result from DR is simple, the complex process involved in the reduction of dimension makes the result (projection) difficult to understand. To better understand this projection, we propose visualization techniques that allow users to simulate change in original features and visualize the corresponding change in the projection.