© 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. 5-CLT-HP
    4. 3221
    Prev
    Next
    INDEX
    Explanations

    conducted

    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
    PreferredItem
    -0.78
    httphttps
    -0.77
    NameInMap
    -0.73
    addCriterion
    -0.68
    ="@+
    -0.67
    oredCriteria
    -0.66
     BorderRadius
    -0.64
    ]--;
    -0.63
     stället
    -0.61
    最快更新
    -0.60
    POSITIVE LOGITS
     by
    1.15
     in
    0.74
     at
    0.71
     By
    0.67
    by
    0.60
     to
    0.56
     and
    0.55
     BY
    0.53
    By
    0.53
     answers
    0.50
    Activations Density 0.004%

    No Known Activations