© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45956
    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
     smoke
    -1.04
     Smoke
    -0.87
    smoke
    -0.83
    Smoke
    -0.83
     smoking
    -0.62
     smoker
    -0.59
     smoked
    -0.57
     smoky
    -0.57
     smokes
    -0.55
     définiti
    -0.53
    POSITIVE LOGITS
    <bos>
    0.60
     betweenstory
    0.57
    mybatisplus
    0.55
    extAlignment
    0.54
    enumii
    0.53
    锈钢
    0.52
     viewDidLoad
    0.52
    VELAND
    0.52
    WillAppear
    0.51
    liseum
    0.51
    Activations Density 0.006%

    No Known Activations