© 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. 77030
    Prev
    Next
    INDEX
    Explanations

    Programming/technical documentation

    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
    емости
    -0.52
     Sén
    -0.52
    Спасылкі
    -0.51
    icata
    -0.51
    塔
    -0.47
    lya
    -0.46
    boli
    -0.46
    acta
    -0.46
    withstanding
    -0.46
     live
    -0.45
    POSITIVE LOGITS
    BeginContext
    0.67
    AsUp
    0.57
    EndProject
    0.53
    endforeach
    0.53
    出版年
    0.52
    mybatisplus
    0.52
     time
    0.52
    GEBURTSDATUM
    0.50
    principalTable
    0.50
     ويكيپيديا
    0.50
    Activations Density 0.002%

    No Known Activations