© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77603
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    TestingModule
    -0.79
    Geplaatst
    -0.71
     AttributeSet
    -0.68
    UnknownFieldSet
    -0.67
    MigrationBuilder
    -0.67
    UserScript
    -0.66
    IsContent
    -0.65
    ValueStyle
    -0.65
    ChildScrollView
    -0.65
    ürzt
    -0.63
    POSITIVE LOGITS
     top
    0.56
     out
    0.52
     outside
    0.49
     first
    0.47
     esterni
    0.43
     ú
    0.40
     very
    0.40
     outer
    0.39
     final
    0.39
     dış
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.