© 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. 1-CLT-HP
    7. 16125
    Prev
    Next
    INDEX
    Explanations

    legal judgements matters

    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
    Negative Logits
     CreateTagHelper
    -0.91
     ویکی‌پدیای
    -0.70
     Jefus
    -0.61
    MigrationBuilder
    -0.60
    :✨
    -0.60
     occaf
    -0.59
    الحياه
    -0.58
     Houſe
    -0.57
    ChildScrollView
    -0.57
     chofe
    -0.56
    POSITIVE LOGITS
    ment
    0.61
     about
    0.59
    ly
    0.56
    al
    0.56
    theless
    0.55
    less
    0.52
     rendu
    0.49
    ness
    0.49
    gonic
    0.48
     Roads
    0.48
    Activations Density 0.004%

    No Known Activations