© 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. 1-CLT-HP
    7. 10179
    Prev
    Next
    INDEX
    Explanations

    painting

    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
    +#+#
    -0.78
    
    -0.68
     HasFactory
    -0.68
     quæ
    -0.68
     مرئيه
    -0.66
     initComponents
    -0.66
    -------------</
    -0.65
    principalColumn
    -0.65
    extAlignment
    -0.65
    fromCharCode
    -0.63
    POSITIVE LOGITS
    isFull
    0.44
     banco
    0.44
     original
    0.43
     hands
    0.43
     Green
    0.43
    writeFieldEnd
    0.43
     purchase
    0.42
     cost
    0.42
     AS
    0.41
    uarts
    0.41
    Activations Density 0.084%

    No Known Activations