© 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. 5-CLT-HP
    7. 6210
    Prev
    Next
    INDEX
    Explanations

    and

    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
     eorum
    -0.63
     habet
    -0.53
     quæ
    -0.52
    Like
    -0.50
     Ones
    -0.50
     fuit
    -0.49
    like
    -0.48
     Like
    -0.48
    hemia
    -0.47
    躇
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.73
     AspNetCore
    0.62
     AssemblyCulture
    0.61
    expandindo
    0.60
     للاسماء
    0.60
     numerus
    0.59
     @"/
    0.59
     NSCoder
    0.56
     unknownFields
    0.55
     Roskov
    0.54
    Activations Density 0.000%

    No Known Activations