© 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. 5-CLT-HP
    7. 92401
    Prev
    Next
    INDEX
    Explanations

    Doug/Douglas

    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
    Douglas
    -0.48
    TryGetValue
    -0.48
     Douglas
    -0.47
    pop
    -0.46
     Doc
    -0.46
    down
    -0.46
     Doug
    -0.45
    وند
    -0.43
    +#+
    -0.41
     doc
    -0.41
    POSITIVE LOGITS
    :✨
    0.73
    AntiForgeryToken
    0.56
    orianCalendar
    0.53
     Neale
    0.52
    läufer
    0.52
     eater
    0.51
    typeorm
    0.49
     oignons
    0.49
     météoro
    0.48
    moires
    0.48
    Activations Density 0.003%

    No Known Activations