© 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. 90904
    Prev
    Next
    INDEX
    Explanations

    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
    yargs
    -0.65
     NSCoder
    -0.62
     aDecoder
    -0.58
     GlobalKey
    -0.56
    InputBorder
    -0.53
    ValueGeneration
    -0.52
    amazonaws
    -0.49
    onedDateTime
    -0.48
     realisation
    -0.47
     Buggy
    -0.47
    POSITIVE LOGITS
    :^(
    0.56
     OFDb
    0.55
    iastes
    0.50
     EconPapers
    0.49
     adds
    0.46
     says
    0.46
     also
    0.45
    Външни
    0.45
    ’
    0.45
     jPanel
    0.44
    Activations Density 0.004%

    No Known Activations