© 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. 9983
    Prev
    Next
    INDEX
    Explanations

    five

    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
    Còn
    -0.63
    Và
    -0.59
    QMetaType
    -0.57
    PORTS
    -0.56
    Népesség
    -0.55
    Kjelder
    -0.55
    Parcelize
    -0.55
    topatho
    -0.54
    :+:
    -0.54
    ruptedException
    -0.54
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
    th
    0.49
     toughest
    0.48
     dernières
    0.48
     Algerian
    0.47
     Fingers
    0.46
     largest
    0.46
    K
    0.45
     senses
    0.45
    شیر
    0.45
    Activations Density 0.009%

    No Known Activations