© 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. 0-CLT-HP
    7. 40591
    Prev
    Next
    INDEX
    Explanations

    copro

    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
    wera
    -0.98
     silhouette
    -0.79
     silhouettes
    -0.77
    DeleteBehavior
    -0.73
     kaynağından
    -0.73
    invokeLater
    -0.69
    Geplaatst
    -0.63
    ozo
    -0.63
    COUVER
    -0.60
     Савезне
    -0.60
    POSITIVE LOGITS
     StatefulWidget
    0.50
     vôtre
    0.50
     conseillers
    0.48
     bénévoles
    0.48
     trámite
    0.47
    sedia
    0.47
     Sanity
    0.47
     coff
    0.47
     vœux
    0.47
    setP
    0.46
    Activations Density 0.289%

    No Known Activations