© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8751
    Prev
    Next
    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Exporter
    -0.63
    Export
    -0.53
     Export
    -0.52
    EXPORT
    -0.52
     export
    -0.51
     import
    -0.51
    ak
    -0.50
     EXPORT
    -0.49
    Imports
    -0.49
     imports
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.86
    ItemBackground
    0.85
    AndEndTag
    0.81
    ViewImports
    0.80
     تضيفلها
    0.77
     ModelRenderer
    0.76
     Савезне
    0.75
    RegressionTest
    0.74
    gonic
    0.74
    MIDDLEWARE
    0.73
    Activations Density 0.105%

    No Known Activations