© 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. 0-RES-MATRYOSHKA-DC
    7. 11327
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of physical substance used in laboratory and industrial contexts

    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
    ice
    -1.53
    ICE
    -1.29
    ices
    -1.20
    ICES
    -0.88
    lice
    -0.71
    iced
    -0.69
    tice
    -0.59
    icing
    -0.59
    icei
    -0.59
    ICED
    -0.57
    POSITIVE LOGITS
     ice
    1.84
     Ice
    1.09
     hielo
    0.95
    Ice
    0.85
     ghiaccio
    0.83
     ijs
    0.79
     helados
    0.79
     iced
    0.75
     helado
    0.66
    冰
    0.66
    Activations Density 0.003%

    No Known Activations