© 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. 6-RES-MATRYOSHKA-DC
    7. 772
    Prev
    Next
    INDEX
    Explanations

    equals signs and related characters in source code and markup languages

    oai_token-act-pair · gemini-2.0-flash
    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
    BeginContext
    -0.77
    UnusedPrivate
    -0.74
    )");
    -0.73
    Попис
    -0.73
    Tikang
    -0.69
    yth
    -0.63
     Patty
    -0.63
    Jeografia
    -0.63
    Становништво
    -0.62
     typelib
    -0.61
    POSITIVE LOGITS
    
    0.67
     =
    0.63
     *=
    0.60
     Upan
    0.60
    ‗
    0.59
     modelAndView
    0.57
    numerusform
    0.56
     Chlorine
    0.56
     medusa
    0.56
     Barnet
    0.56
    Activations Density 0.363%

    No Known Activations