© 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. 1-CLT-HP
    7. 8922
    Prev
    Next
    INDEX
    Explanations

    from

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.02
    AddTagHelper
    -0.80
    webElementXpaths
    -0.77
    SourceChecksum
    -0.73
     Roskov
    -0.71
    rungsseite
    -0.70
     @"/
    -0.70
    ftagPool
    -0.69
     '{@
    -0.69
    tableFuture
    -0.69
    POSITIVE LOGITS
     birth
    0.50
     pregnancy
    0.46
     bloodstream
    0.43
     uterus
    0.42
     placental
    0.42
     procedures
    0.41
     miscarriage
    0.41
     headache
    0.41
     thromb
    0.41
     uterine
    0.40
    Activations Density 0.014%

    No Known Activations