© 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. 20-CLT-HP
    7. 73089
    Prev
    Next
    INDEX
    Explanations

    code, names, and news

    np_max-act-logits · 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
    رشف
    -0.56
    ppler
    -0.47
    askan
    -0.41
    Vanjske
    -0.41
    SqlSession
    -0.39
     hız
    -0.38
     étudi
    -0.38
    énario
    -0.38
    wohner
    -0.37
    ขาย
    -0.37
    POSITIVE LOGITS
    MigrationBuilder
    0.61
    — 
    0.61
    CreateModel
    0.60
    exitRule
    0.60
     متعلقه
    0.58
    Tembelea
    0.57
     صوتيه
    0.57
    endphp
    0.55
    pe
    0.55
    AutoScale
    0.55
    Activations Density 0.000%

    No Known Activations