© 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. 1-CLT-HP
    7. 10256
    Prev
    Next
    INDEX
    Explanations

    river

    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
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.69
    oredCriteria
    -0.64
    MLLoader
    -0.63
    arsky
    -0.59
    ModelAdmin
    -0.57
     Gust
    -0.53
     deceptive
    -0.52
    affaires
    -0.52
    хьтан
    -0.52
    afu
    -0.52
    POSITIVE LOGITS
     ModelExpression
    0.49
    허
    0.45
    brada
    0.44
    bed
    0.44
     VIDEOTAPE
    0.44
    合衆
    0.43
    birds
    0.42
    agem
    0.42
    ậc
    0.42
    books
    0.41
    Activations Density 0.005%

    No Known Activations