© 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. 0-CLT-HP
    7. 43104
    Prev
    Next
    INDEX
    Explanations

    data science

    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
    InputBorder
    -0.98
     itſelf
    -0.96
     Efq
    -0.92
     الرياضيه
    -0.92
     Monfieur
    -0.90
     كومونز
    -0.89
     iſt
    -0.88
     Shakspeare
    -0.87
     ProtoMessage
    -0.86
    Vidite
    -0.84
    POSITIVE LOGITS
    ness
    0.70
     for
    0.62
     of
    0.62
     in
    0.54
     (
    0.54
    ,
    0.53
     to
    0.52
    nya
    0.52
     so
    0.51
    sets
    0.50
    Activations Density 0.313%

    No Known Activations