© 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. 91081
    Prev
    Next
    INDEX
    Explanations

    titles with dates and names

    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
    KommentareTeilen
    -0.56
    forName
    -0.53
    arch
    -0.52
    aris
    -0.52
     newInstance
    -0.50
     magn
    -0.48
    invokeLater
    -0.48
    match
    -0.47
     magnifying
    -0.47
    naeus
    -0.47
    POSITIVE LOGITS
    NewUrlParser
    0.73
    transQ
    0.66
     beginnetje
    0.59
    WriteLiteral
    0.59
     @"/
    0.56
     elettrico
    0.54
    tanooga
    0.54
    TagMode
    0.52
    MigrationBuilder
    0.49
     mussels
    0.49
    Activations Density 0.000%

    No Known Activations