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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 490
    Prev
    Next
    INDEX
    Explanations

    exchange

    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
     exchange
    -1.46
    exchange
    -1.32
     Exchange
    -1.27
    Exchange
    -1.26
     EXCHANGE
    -1.16
     exchanged
    -0.98
     exchanging
    -0.97
    EXCHANGE
    -0.91
     exchanges
    -0.84
    échange
    -0.83
    POSITIVE LOGITS
    cplusplus
    0.52
    ftagPool
    0.52
     filled
    0.50
    Acta
    0.50
     wypeł
    0.48
    nonatomic
    0.47
     for
    0.47
     Filled
    0.47
    :✨
    0.47
    ukunft
    0.47
    Activations Density 0.066%

    No Known Activations