© 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. 5-CLT-HP
    7. 91392
    Prev
    Next
    INDEX
    Explanations

    central connection points

    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
    最快更新
    -0.68
    ConstraintMaker
    -0.65
    UserScript
    -0.65
     ProtoMessage
    -0.63
     שוליים
    -0.62
    
    -0.60
    脚注の使い方
    -0.60
    Välislingid
    -0.59
     Walkover
    -0.59
    ajs
    -0.58
    POSITIVE LOGITS
     for
    0.72
     airport
    0.55
    contentLoaded
    0.54
    town
    0.52
     between
    0.50
     town
    0.46
     to
    0.45
     on
    0.43
    Функ
    0.42
     function
    0.41
    Activations Density 0.003%

    No Known Activations