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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45462
    Prev
    Next
    INDEX
    Explanations

    spar

    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
     spar
    -1.65
     Spar
    -1.52
    spar
    -1.44
    Spar
    -1.41
     spars
    -1.12
     SPAR
    -0.91
    SPAR
    -0.77
     sparring
    -0.66
     sparrows
    -0.61
    WebVitals
    -0.59
    POSITIVE LOGITS
    spół
    0.50
     anthropology
    0.50
     vost
    0.48
    TagMode
    0.47
    setVerticalGroup
    0.46
    kulum
    0.46
     absc
    0.44
    ยาย
    0.43
    rrrrrrrr
    0.43
     hellen
    0.42
    Activations Density 0.004%

    No Known Activations