© 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. 1938
    Prev
    Next
    INDEX
    Explanations

    Cochrane

    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
    o
    -1.09
    a
    -0.98
    y
    -0.86
    e
    -0.81
    i
    -0.74
     UPM
    -0.74
     Mahomet
    -0.73
    ه
    -0.72
     DRM
    -0.70
    en
    -0.68
    POSITIVE LOGITS
    exprimer
    0.61
     ProtoMessage
    0.61
    PerformLayout
    0.59
     فريبيس
    0.56
    autorisation
    0.55
    écart
    0.54
     Mill
    0.54
     Imp
    0.53
     Der
    0.52
    æus
    0.52
    Activations Density 0.215%

    No Known Activations