© 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. 15684
    Prev
    Next
    INDEX
    Explanations

    lists

    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
    tima
    -0.69
    posa
    -0.64
     Andrea
    -0.57
    Andrea
    -0.54
    CrossRef
    -0.52
    ArgumentParser
    -0.50
     continúas
    -0.50
    lano
    -0.49
    例文帳に追加
    -0.49
    : 
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.57
     >=",
    0.56
    Chham
    0.55
     اكتوبر
    0.54
     betek
    0.52
    ezers
    0.52
    @[+][
    0.51
     mecán
    0.50
     appétit
    0.50
     Watched
    0.50
    Activations Density 0.012%

    No Known Activations