© 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. 6244
    Prev
    Next
    INDEX
    Explanations

    continents/regions

    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
     AssemblyCulture
    -0.59
    хьтан
    -0.53
    stylers
    -0.50
     BoxFit
    -0.47
    strix
    -0.47
    ConverterFactory
    -0.47
    RefreshLayout
    -0.47
    chimp
    -0.46
     protoimpl
    -0.45
    racuda
    -0.44
    POSITIVE LOGITS
    Rujukan
    0.65
     EconPapers
    0.63
    Hochspringen
    0.62
    Tembelea
    0.57
     finestra
    0.57
     Roskov
    0.56
     politiet
    0.56
    studi
    0.56
     Studi
    0.55
     légales
    0.54
    Activations Density 0.002%

    No Known Activations