© 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. 15171
    Prev
    Next
    INDEX
    Explanations

    resistant

    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
     betweenstory
    -0.72
     nahilalakip
    -0.69
     MenuView
    -0.61
    
    -0.60
     Pendleton
    -0.60
     odkazy
    -0.58
     foncé
    -0.57
    InSection
    -0.56
     Hertz
    -0.56
    Begriffsklä
    -0.56
    POSITIVE LOGITS
     Signalez
    0.57
     للاسماء
    0.57
     NSCoder
    0.57
     HasFactory
    0.52
    marvin
    0.47
     SUDOC
    0.46
    Segoe
    0.45
    GRACE
    0.45
    Historical
    0.43
    TRAILING
    0.43
    Activations Density 0.016%

    No Known Activations