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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12645
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     d
    -0.53
     miss
    -0.52
     po
    -0.52
    zuführen
    -0.52
     a
    -0.51
     n
    -0.49
     m
    -0.49
     to
    -0.48
     me
    -0.48
     i
    -0.47
    POSITIVE LOGITS
     itſelf
    0.88
     auroit
    0.82
     feroit
    0.78
     avoient
    0.77
    ſelf
    0.75
     raiſ
    0.75
     Reſ
    0.74
     pouvoit
    0.74
     ་་
    0.74
     auffi
    0.73
    Activations Density 0.024%

    No Known Activations