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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13483
    Prev
    Next
    INDEX
    Explanations

    architecture

    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
    पया
    -0.74
     pinulongan
    -0.68
    Jeografia
    -0.64
     Exacts
    -0.63
     Exactos
    -0.62
    клопе
    -0.62
    istoitu
    -0.62
    ColumnHeaders
    -0.62
    Билгалдахарш
    -0.60
     typelib
    -0.60
    POSITIVE LOGITS
    dedor
    0.51
     oignons
    0.45
    TRACT
    0.45
    PhysRev
    0.45
     Scot
    0.44
    isku
    0.44
    شعر
    0.44
    öld
    0.44
     Cooks
    0.44
    ergies
    0.43
    Activations Density 0.053%

    No Known Activations