© 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. 4-CLT-HP
    7. 4678
    Prev
    Next
    INDEX
    Explanations

    to

    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
     صوتيه
    -0.94
    出版年
    -0.91
    RegressionTest
    -0.83
    ImageContext
    -0.80
    TagMode
    -0.80
    EndGlobalSection
    -0.79
    msgTypes
    -0.79
    rrggbb
    -0.77
    elemField
    -0.77
    ThroughAttribute
    -0.75
    POSITIVE LOGITS
     sus
    0.52
     supplement
    0.51
     guide
    0.50
     match
    0.47
     complement
    0.46
     cope
    0.45
     deal
    0.45
     get
    0.44
     gel
    0.41
     fully
    0.41
    Activations Density 0.015%

    No Known Activations