© 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. 20-CLT-HP
    7. 76408
    Prev
    Next
    INDEX
    Explanations

    say "number"

    np_max-act-logits · 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
    Sixth
    -0.58
    abetes
    -0.57
    bootstrapcdn
    -0.55
    saraba
    -0.54
     sixth
    -0.54
    adpleegd
    -0.53
    GHIJKLM
    -0.53
    beitet
    -0.53
     Allociné
    -0.52
     وتسجيلات
    -0.52
    POSITIVE LOGITS
     intptr
    0.61
    localctx
    0.57
    ClientSize
    0.56
    참고
    0.56
    jmniej
    0.56
     eighties
    0.54
    jooq
    0.51
    Sursa
    0.50
     Parr
    0.48
     xviii
    0.47
    Activations Density 0.004%

    No Known Activations