© 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. 3097
    Prev
    Next
    INDEX
    Explanations

    file names and types

    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
    -0.61
     '\\;'
    -0.54
    ChildScrollView
    -0.53
    trze
    -0.52
    modb
    -0.51
    withOpacity
    -0.50
     Soccerway
    -0.50
    ViewById
    -0.49
    arounds
    -0.49
    ulary
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.77
     חיצוניים
    0.50
    RenderAtEndOf
    0.47
    unknownFields
    0.46
    rowable
    0.46
     McF
    0.46
     linkovi
    0.45
     κύ
    0.45
    ногие
    0.44
     ProtoMessage
    0.41
    Activations Density 0.009%

    No Known Activations