© 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. 0-CLT-HP
    7. 95491
    Prev
    Next
    INDEX
    Explanations

    sorts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     societies
    -1.01
     Societies
    -0.88
    帖最后由
    -0.87
     formats
    -0.85
     watersheds
    -0.83
     Formats
    -0.83
     Easter
    -0.82
     easter
    -0.80
     sorts
    -0.79
    thâu
    -0.77
    POSITIVE LOGITS
     of
    0.53
    ChildScrollView
    0.49
     Step
    0.46
    Step
    0.45
     ris
    0.45
     The
    0.43
    LY
    0.43
    ira
    0.42
     muun
    0.42
    fprintf
    0.41
    Activations Density 0.222%

    No Known Activations