© 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. 1-CLT-HP
    7. 14837
    Prev
    Next
    INDEX
    Explanations

    ney

    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
     pitié
    -0.59
     nemlig
    -0.57
    Portale
    -0.56
     typelib
    -0.54
     vaisselle
    -0.53
     trasporto
    -0.52
    PMailer
    -0.52
     namelijk
    -0.52
     creș
    -0.52
    BibitemOpen
    -0.51
    POSITIVE LOGITS
    StructEnd
    0.73
    ียบ
    0.58
    house
    0.56
     oprot
    0.55
    table
    0.53
    DotNetBar
    0.51
    FontOfSize
    0.50
    tvguidetime
    0.49
     stal
    0.49
    THO
    0.49
    Activations Density 0.048%

    No Known Activations