© 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. 76593
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.82
     Utf
    -0.71
    complexContent
    -0.69
    MigrationBuilder
    -0.69
     ModelExpression
    -0.69
     Paglinawan
    -0.68
    WriteTagHelper
    -0.67
     ErrIntOverflow
    -0.66
     Wikimedijinoj
    -0.62
    mapStateToProps
    -0.62
    POSITIVE LOGITS
     st
    0.40
    زاده
    0.36
    Phy
    0.36
    yorsunuz
    0.36
    ที่
    0.36
    unt
    0.36
    aimer
    0.36
    yors
    0.36
    ジェ
    0.35
     Phy
    0.35
    Activations Density 0.002%

    No Known Activations