© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13675
    Prev
    Next
    INDEX
    Explanations

    work

    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
    ținut
    -0.60
     jegy
    -0.56
    ffo
    -0.56
     défendre
    -0.54
    BagLayout
    -0.54
    idenz
    -0.54
     négo
    -0.53
     connaît
    -0.52
     exécut
    -0.52
    $_['
    -0.52
    POSITIVE LOGITS
     Biôgrafia
    0.65
     AssemblyCulture
    0.61
     ویکی‌پدی
    0.56
    UnusedPrivate
    0.52
    
    0.52
     tartalomajánló
    0.51
     distanciation
    0.51
     nahilalakip
    0.51
     հղումներ
    0.50
    FunctionFlags
    0.50
    Activations Density 0.023%

    No Known Activations