© 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. 15363
    Prev
    Next
    INDEX
    Explanations

    fish

    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
    fishes
    -0.54
    opsida
    -0.52
    zboi
    -0.51
    calientes
    -0.50
    ünsche
    -0.50
    afficheront
    -0.49
    ctools
    -0.47
    qvist
    -0.47
    empuan
    -0.47
     Macmillan
    -0.47
    POSITIVE LOGITS
     виправивши
    0.63
    kloped
    0.56
     فريبيس
    0.55
    JdbcTemplate
    0.54
    UpInside
    0.54
    ereich
    0.52
    mo
    0.51
     nahilalakip
    0.50
     دیکھیے
    0.50
    ting
    0.50
    Activations Density 0.444%

    No Known Activations