© 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. 92237
    Prev
    Next
    INDEX
    Explanations

    Clay

    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
     بيها
    -0.49
    XMLSchema
    -0.48
     يتيمه
    -0.47
     chande
    -0.47
     di
    -0.46
    acing
    -0.46
     stär
    -0.45
     مشين
    -0.45
    <thead>
    -0.44
     péri
    -0.44
    POSITIVE LOGITS
    findpost
    0.61
    RenderAtEndOf
    0.60
     للمعارف
    0.59
    tor
    0.58
    ViewFeatures
    0.56
    dafx
    0.55
    ThroughAttribute
    0.55
    ValueGenerated
    0.53
     ModelExpression
    0.53
     Servlet
    0.52
    Activations Density 0.004%

    No Known Activations