© 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. 78265
    Prev
    Next
    INDEX
    Explanations

    Scientific or academic texts

    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
    WindowEvent
    -0.60
    
    -0.60
    thâu
    -0.57
     Wikimedijinoj
    -0.54
    WindowConstants
    -0.54
    adpleegd
    -0.53
     कैसी
    -0.52
     tepung
    -0.50
     mergeFrom
    -0.50
    ้อง
    -0.50
    POSITIVE LOGITS
    UPAC
    0.51
    Dış
    0.51
     Education
    0.50
     Logic
    0.49
     AssemblyCulture
    0.48
    icose
    0.48
     Supplemental
    0.48
     Dreyfus
    0.47
     للاسماء
    0.47
     Assignee
    0.46
    Activations Density 0.000%

    No Known Activations