© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12258
    Prev
    Next
    INDEX
    Explanations

    Smoking

    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
    smoking
    -0.95
     Smoking
    -0.91
     Smo
    -0.91
     smoking
    -0.91
     smoker
    -0.90
    Smo
    -0.87
     smokes
    -0.85
    Smoking
    -0.84
     smokers
    -0.81
     smoke
    -0.78
    POSITIVE LOGITS
    '])->
    0.59
    })->
    0.55
     مرئيه
    0.53
    ]');
    0.48
    पया
    0.47
    ')->
    0.47
    Gweler
    0.47
    .
    0.46
    ]').
    0.45
    ")->
    0.43
    Activations Density 0.020%

    No Known Activations