© 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. 6388
    Prev
    Next
    INDEX
    Explanations

    structures related to data formatting, particularly focusing on code, tables, or organized information

    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
    queryInterface
    -0.75
    RRect
    -0.57
    ↵↵
    -0.53
    LikeLiked
    -0.52
     lateinit
    -0.50
    drawSprites
    -0.49
    ellees
    -0.49
     ویکی‌آمباردا
    -0.49
    تقاوى
    -0.48
    렴
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.94
    tvguidetime
    0.75
     nakalista
    0.75
    }{*}{}
    0.64
    <bos>
    0.63
    日閲覧
    0.63
    +:+
    0.58
    #
    0.57
    ctique
    0.56
    adecimal
    0.56
    Activations Density 1.562%

    No Known Activations