© 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. 2-RES-MATRYOSHKA-DC
    7. 3230
    Prev
    Next
    INDEX
    Explanations

    mentions of wine or wineries

    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
     pitié
    -0.63
     pauvres
    -0.60
     Brito
    -0.59
     مشين
    -0.59
     kebersihan
    -0.58
     bonté
    -0.58
     dår
    -0.57
     morire
    -0.57
    CONSOLE
    -0.57
     Escolar
    -0.56
    POSITIVE LOGITS
     wine
    2.98
     Wine
    2.70
     wines
    2.64
    Wine
    2.63
    wine
    2.45
     WINE
    2.45
     Wines
    2.14
     winery
    2.00
     wineries
    1.93
     vineyard
    1.91
    Activations Density 0.027%

    No Known Activations