Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11113
    Prev
    Next
    INDEX
    Explanations

    when

    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
    참고
    -0.86
     muualla
    -0.61
     prefent
    -0.60
    Gön
    -0.59
     poffible
    -0.58
     propTypes
    -0.57
     ContentValues
    -0.56
     laft
    -0.56
    HasColumnType
    -0.56
     laſt
    -0.55
    POSITIVE LOGITS
     the
    0.64
     seeing
    0.56
     I
    0.54
     enjoying
    0.50
     enjoy
    0.50
     x
    0.46
     we
    0.46
    WaitGroup
    0.46
     ***!
    0.45
    utex
    0.45
    Activations Density 0.032%

    No Known Activations