© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92894
    Prev
    Next
    INDEX
    Explanations

    code/logs/papers

    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
    olella
    -0.47
     désolés
    -0.45
     للاسماء
    -0.44
    AddHtmlAttribute
    -0.43
     برانيه
    -0.42
    label
    -0.41
    agi
    -0.41
     oprot
    -0.40
     ModelExpression
    -0.40
    Portály
    -0.40
    POSITIVE LOGITS
     againſt
    0.64
     themſelves
    0.63
     مواليد
    0.63
    NUMX
    0.62
    Brainz
    0.61
     RIPRODUZIONE
    0.61
     BoxFit
    0.60
     >",
    0.60
     itſelf
    0.59
    ^(@)
    0.59
    Activations Density 0.001%

    No Known Activations