© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13633
    Prev
    Next
    INDEX
    Explanations

    page word

    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
    ing
    -0.59
    pages
    -0.55
    page
    -0.48
     humanas
    -0.48
     pages
    -0.47
    ry
    -0.47
    Page
    -0.45
    Of
    -0.45
     artistico
    -0.45
    版
    -0.44
    POSITIVE LOGITS
     Wikispecies
    0.77
     createSprite
    0.75
    encodeWith
    0.71
    wpi
    0.70
    DoubleQuotes
    0.69
     /\.
    0.69
    ConstraintMaker
    0.69
    ChildScrollView
    0.69
    脚注の使い方
    0.67
    makeConstraints
    0.65
    Activations Density 0.006%

    No Known Activations