© 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. 0-CLT-HP
    7. 95164
    Prev
    Next
    INDEX
    Explanations

    Code/Web files

    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
    hle
    -2.53
    hlen
    -0.56
    mouthed
    -0.55
    providedIn
    -0.54
    marvin
    -0.52
    uarts
    -0.52
    Eksteraj
    -0.51
    ngdoc
    -0.50
    hled
    -0.50
    Grip
    -0.49
    POSITIVE LOGITS
    sidemargin
    0.90
    IndentedString
    0.74
    DoubleQuotes
    0.73
     ModelExpression
    0.62
     kaynağından
    0.58
     EconPapers
    0.57
    transQ
    0.54
     yyl
    0.50
    ierać
    0.49
    cyklopedia
    0.48
    Activations Density 0.138%

    No Known Activations