© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71655
    Prev
    Next
    INDEX
    Explanations

    Ann

    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
    ImageContext
    -0.85
    ConstraintMaker
    -0.80
    الدراسه
    -0.71
     незавершена
    -0.71
    قایناق‌لار
    -0.67
    SharedCtor
    -0.66
     aDecoder
    -0.61
    setViewportView
    -0.61
     Wikimedijinoj
    -0.59
    pædia
    -0.57
    POSITIVE LOGITS
     يتيمه
    0.57
    ειν
    0.57
    fastjson
    0.53
     nameof
    0.47
    issory
    0.47
    ngx
    0.46
    inį
    0.45
     SFR
    0.45
    Обо
    0.44
     numerus
    0.44
    Activations Density 0.000%

    No Known Activations