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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94246
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    الحياه
    -0.59
    skjaer
    -0.50
    mphony
    -0.50
    россий
    -0.48
     الدولى
    -0.48
    adget
    -0.48
    getItemId
    -0.48
     Bourgoin
    -0.48
    cass
    -0.47
     yaw
    -0.47
    POSITIVE LOGITS
    IUrlHelper
    0.66
     ProtoMessage
    0.63
     שוליים
    0.60
     الاطلاع
    0.57
    addCriterion
    0.57
     wikipagina
    0.55
    setOnAction
    0.55
    orteur
    0.54
     rigue
    0.54
    তথ্যসূত্র
    0.54
    Activations Density 0.002%

    No Known Activations