© 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. 4992
    Prev
    Next
    INDEX
    Explanations

    upcoming events

    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
    Personensuche
    -0.68
    Portály
    -0.66
     ویکی‌پدیا
    -0.60
    PickerController
    -0.57
    Descripció
    -0.56
    XMLSchema
    -0.56
    parseColor
    -0.52
    ofman
    -0.50
    jsoup
    -0.49
    ctools
    -0.49
    POSITIVE LOGITS
     federally
    0.48
     really
    0.48
     quickly
    0.48
    LookAnd
    0.47
     on
    0.46
    sect
    0.46
     Wicidata
    0.46
     soon
    0.46
    actu
    0.46
     rápido
    0.45
    Activations Density 0.004%

    No Known Activations