© 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. 71539
    Prev
    Next
    INDEX
    Explanations

    Technical and uncommon text

    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
    Negative Logits
    MessageOf
    -0.61
    urlpatterns
    -0.57
    WireFormatLite
    -0.53
    mybatisplus
    -0.53
    flikt
    -0.52
    LookAnd
    -0.52
    jupiter
    -0.50
    новништво
    -0.49
    :+:
    -0.48
    Gambas
    -0.48
    POSITIVE LOGITS
    колко
    0.52
     يتيمه
    0.47
     Weiz
    0.45
    ̣c
    0.44
     Borel
    0.43
    ió
    0.43
     etre
    0.42
    xea
    0.42
    ButtonClicked
    0.42
    로그
    0.42
    Activations Density 0.001%

    No Known Activations