© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98131
    Prev
    Next
    INDEX
    Explanations

    today

    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
    expandindo
    -0.82
    AddTagHelper
    -0.75
    ConstraintMaker
    -0.72
    InjectAttribute
    -0.71
     sánh
    -0.71
     builds
    -0.68
    ThroughAttribute
    -0.67
    contentLoaded
    -0.66
     getItemId
    -0.66
    IANGLES
    -0.65
    POSITIVE LOGITS
    ,
    0.48
     insectes
    0.47
     înainte
    0.46
     popoli
    0.45
    .
    0.43
    XmlAccessType
    0.43
     domésticos
    0.42
     eje
    0.42
    וויק
    0.42
    ietal
    0.41
    Activations Density 0.003%

    No Known Activations