© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 1038
    Prev
    Next
    INDEX
    Explanations

    found

    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
    큼
    -0.66
     purpoſe
    -0.65
     fhew
    -0.65
     Efq
    -0.62
     poffible
    -0.62
    :+:
    -0.61
    provisional
    -0.60
     microfiber
    -0.59
     ſtand
    -0.57
    IntoConstraints
    -0.55
    POSITIVE LOGITS
    ьаж
    0.53
    település
    0.52
    mybatisplus
    0.48
    الحياه
    0.46
    ViewImports
    0.45
     تضيفلها
    0.44
    SuppressMessage
    0.43
    الدراسه
    0.42
    addCriterion
    0.42
     trattano
    0.41
    Activations Density 0.068%

    No Known Activations