© 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. 91158
    Prev
    Next
    INDEX
    Explanations

    carbon

    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
     carbon
    -2.80
     Carbon
    -2.48
    Carbon
    -2.19
     CARBON
    -2.17
    carbon
    -2.13
    CARBON
    -1.69
     carbono
    -1.63
     karbon
    -1.59
    碳
    -1.45
     carbone
    -1.45
    POSITIVE LOGITS
     dioxide
    0.96
    ization
    0.91
    ized
    0.82
     tetrachloride
    0.76
    izations
    0.76
    izing
    0.75
     monoxide
    0.73
    isation
    0.69
     '\\;'
    0.67
    ised
    0.66
    Activations Density 0.060%

    No Known Activations