© 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. 6017
    Prev
    Next
    INDEX
    Explanations

    increasing

    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
    AddHtmlAttribute
    -0.69
     néz
    -0.62
    ftagPool
    -0.59
    @[+][
    -0.57
    linie
    -0.56
    лактика
    -0.55
    éton
    -0.55
    Демографія
    -0.54
     regole
    -0.54
     chère
    -0.54
    POSITIVE LOGITS
     attention
    0.71
     numbers
    0.60
     proportions
    0.52
     quantities
    0.52
     emphasis
    0.49
     amounts
    0.48
     uſe
    0.48
    attention
    0.46
    enced
    0.46
     partici
    0.45
    Activations Density 0.003%

    No Known Activations