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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1657
    Prev
    Next
    INDEX
    Explanations

    mentions of smoking or tobacco use

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Klu
    -0.69
     Gor
    -0.62
     Zain
    -0.61
     Munster
    -0.60
    /*---
    -0.60
    CascadeType
    -0.58
    endmodule
    -0.57
     Peas
    -0.57
    ệt
    -0.57
    ufer
    -0.57
    POSITIVE LOGITS
     smoking
    2.09
     Smoking
    2.03
     smoker
    1.96
     smoke
    1.95
     smokers
    1.89
    Smoking
    1.87
    smoking
    1.86
     Smo
    1.84
    Smo
    1.79
     Smoke
    1.78
    Activations Density 2.847%

    No Known Activations