© 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. 1-RES-MATRYOSHKA-DC
    7. 734
    Prev
    Next
    INDEX
    Explanations

    references to the symbol "*~" with high certainty

    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
    Datuak
    -0.91
     endwhile
    -0.79
    sizeCache
    -0.79
    ]";
    -0.78
    "]();
    -0.73
     Roskov
    -0.73
    %");
    -0.73
    endpush
    -0.71
    VersionUID
    -0.71
    %")
    -0.71
    POSITIVE LOGITS
    *~
    3.55
    *~*~
    1.44
     stock
    0.90
    *^
    0.77
    *-
    0.77
    @~
    0.75
     Stock
    0.70
    Stock
    0.70
     evolution
    0.67
     via
    0.66
    Activations Density 0.329%

    No Known Activations