© 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. 6029
    Prev
    Next
    INDEX
    Explanations

    mixed text snippets

    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
    anthrene
    -0.52
    pergillus
    -0.52
    windowFixed
    -0.51
    will
    -0.50
    builds
    -0.50
    pushFollow
    -0.50
     directs
    -0.49
     picks
    -0.49
    dotenv
    -0.48
    serviceWorker
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.84
     of
    0.72
    sidemargin
    0.57
     démocr
    0.56
     médical
    0.55
     Хорошо
    0.55
     indépend
    0.55
     Sehingga
    0.54
     Sementara
    0.54
    akaian
    0.53
    Activations Density 0.014%

    No Known Activations