© 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. 6325
    Prev
    Next
    INDEX
    Explanations

    references to the section marker for legal or official documents

    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
     pleaſure
    -0.64
    oredCriteria
    -0.64
     Efq
    -0.63
     uſed
    -0.62
     uſe
    -0.61
     ſever
    -0.61
     Jaeger
    -0.59
     juſt
    -0.59
    sedown
    -0.57
     juſ
    -0.57
    POSITIVE LOGITS
    §
    3.00
     §
    1.49
     §§
    1.04
     §.
    0.95
     (§
    0.81
    {§
    0.79
    GOTREF
    0.70
    InSection
    0.69
    ‡
    0.67
     ویکی‌پدیا
    0.66
    Activations Density 0.002%

    No Known Activations