© 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. 0-CLT-HP
    7. 43646
    Prev
    Next
    INDEX
    Explanations

    lazy

    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
     currently
    -0.90
    currently
    -0.75
     presently
    -0.73
    lazy
    -0.71
     Com
    -0.70
    Com
    -0.68
    c
    -0.66
     lazy
    -0.62
     actuellement
    -0.61
    Currently
    -0.58
    POSITIVE LOGITS
     ProtoMessage
    0.97
    SequentialGroup
    0.90
     itſelf
    0.84
     للاسماء
    0.84
     Chriſt
    0.83
    neſs
    0.82
    InvalidProtocol
    0.81
     Chriftian
    0.80
     Jefus
    0.79
    SourceChecksum
    0.79
    Activations Density 0.146%

    No Known Activations