© 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. 0-CLT-HP
    7. 40036
    Prev
    Next
    INDEX
    Explanations

    match

    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
     ones
    -0.98
     match
    -0.77
     race
    -0.71
     Ones
    -0.68
     RACE
    -0.66
     Race
    -0.64
    Còn
    -0.63
     Matching
    -0.63
     MATCH
    -0.62
     matching
    -0.62
    POSITIVE LOGITS
     of
    0.71
    book
    0.63
    port
    0.59
    time
    0.59
    way
    0.59
    ho
    0.56
    let
    0.56
    !
    0.56
    y
    0.55
    plan
    0.54
    Activations Density 0.306%

    No Known Activations