© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2828
    Prev
    Next
    INDEX
    Explanations

    owned

    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
    expandindo
    -0.84
    DockStyle
    -0.82
     مشين
    -0.77
    Personensuche
    -0.76
    Datuak
    -0.74
     nahilalakip
    -0.73
    IntoConstraints
    -0.70
     "..\..\
    -0.67
    
    -0.65
    tonode
    -0.65
    POSITIVE LOGITS
     and
    0.63
     by
    0.54
    glises
    0.52
     imprimée
    0.50
    skosten
    0.50
     singly
    0.50
    elezo
    0.50
     vitesses
    0.50
     coûts
    0.49
     poignée
    0.49
    Activations Density 0.005%

    No Known Activations