© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12872
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific code pattern or sequence, particularly the sequence "xe" with high activation values

    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
    addSubview
    -0.66
    Czytaj
    -0.66
     Италијани
    -0.66
     endblock
    -0.64
    SequentialGroup
    -0.64
     addSubview
    -0.63
    addContainerGap
    -0.61
     ap
    -0.59
     SEDS
    -0.59
     "..\..\..\
    -0.59
    POSITIVE LOGITS
     xe
    1.62
    API
    0.68
    api
    0.67
    MENAFN
    0.61
     API
    0.57
    icoot
    0.54
     RVA
    0.54
     Xe
    0.54
    BrowserRouter
    0.52
    creatic
    0.50
    Activations Density 0.001%

    No Known Activations