© 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. 6512
    Prev
    Next
    INDEX
    Explanations

    references to ice and ice-related objects or concepts

    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
    DoubleQuotes
    -0.74
    ParallelGroup
    -0.69
    inobu
    -0.68
    Tania
    -0.63
    InputModule
    -0.62
    nextProps
    -0.62
    kian
    -0.61
    veloppe
    -0.60
    quero
    -0.60
    StoryboardSegue
    -0.60
    POSITIVE LOGITS
     ice
    3.52
     Ice
    3.19
    Ice
    2.97
    ice
    2.70
     ICE
    2.61
    ICE
    2.28
     hielo
    1.99
     ijs
    1.95
    冰
    1.89
     ghiaccio
    1.77
    Activations Density 0.050%

    No Known Activations