© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    segments of text that contain code or technical notation

    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
    TagMode
    -1.10
    verwijspagina
    -0.93
    )++;
    -0.93
    '])->
    -0.93
     estimés
    -0.91
     &___
    -0.90
    parsedMessage
    -0.90
    queryInterface
    -0.89
    "])
    -0.89
    Personensuche
    -0.88
    POSITIVE LOGITS
    [
    0.60
    1
    0.56
    .
    0.54
    (
    0.53
    {
    0.52
    2
    0.50
     Linie
    0.46
     dets
    0.46
    3
    0.46
    6
    0.46
    Activations Density 0.412%

    No Known Activations