© 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. 3266
    Prev
    Next
    INDEX
    Explanations

    references to symbolic entities like symbols, symbols, or symbol-related terminology

    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
    icon
    -0.84
    ICON
    -0.74
    :✨
    -0.69
    awtextra
    -0.68
    Icon
    -0.66
     wireType
    -0.61
    findpost
    -0.60
    avatar
    -0.59
     Andreas
    -0.59
    gangen
    -0.57
    POSITIVE LOGITS
     symbols
    2.66
     symbol
    2.59
     Symbols
    2.48
    symbol
    2.47
    Symbol
    2.39
     Symbol
    2.39
    symbols
    2.34
     SYMBOL
    2.34
    Symbols
    2.27
    SYMBOL
    2.14
    Activations Density 0.053%

    No Known Activations