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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95229
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     Winaray
    -0.61
     glyphicon
    -0.60
    implement
    -0.56
    makeConstraints
    -0.56
     Waray
    -0.56
     pazi
    -0.56
     interleukin
    -0.55
     pinulongan
    -0.54
     lī
    -0.54
    express
    -0.53
    POSITIVE LOGITS
    TintMode
    0.54
    ”
    0.53
    évaluateur
    0.50
    parsedMessage
    0.50
    devamını
    0.48
    SharedDtor
    0.47
    *************/
    0.47
    :+:
    0.46
     مشين
    0.46
    rouvez
    0.46
    Activations Density 0.021%

    No Known Activations