© 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. 22-RES-MATRYOSHKA-DC
    7. 1677
    Prev
    Next
    INDEX
    Explanations

    words related to cigarettes, smoking, and tobacco

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.88
    XmlAccessType
    -0.78
    GenerationType
    -0.71
    AxisAlignment
    -0.70
    ContentAsync
    -0.68
     bezeichneter
    -0.68
    SBATCH
    -0.67
     feldspar
    -0.67
    URLException
    -0.67
    URIComponent
    -0.66
    POSITIVE LOGITS
     smoking
    1.63
     smokers
    1.52
     smoke
    1.52
     tobacco
    1.42
     cigarette
    1.41
     Smoking
    1.40
     nicotine
    1.39
     smoker
    1.38
     cigarettes
    1.35
     smoked
    1.31
    Activations Density 0.538%

    No Known Activations