© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12354
    Prev
    Next
    INDEX
    Explanations

    references to alcoholic beverages or liquor

    oai_token-act-pair · gpt-4.1-nano
    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
    DeleteCommand
    -0.57
     interesses
    -0.56
    InjectAttribute
    -0.56
    DockStyle
    -0.56
     endwhile
    -0.54
    Extinguishing
    -0.53
    extrême
    -0.53
    awtextra
    -0.52
    SharedDtor
    -0.52
     Barrier
    -0.52
    POSITIVE LOGITS
     liquor
    2.81
     liquors
    2.63
     Liquor
    2.34
    liqu
    2.16
    Liqu
    2.13
     Liqu
    1.96
     liqu
    1.28
     liquef
    1.02
    lique
    0.91
     liqueur
    0.90
    Activations Density 0.002%

    No Known Activations