© 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. 3-RES-MATRYOSHKA-DC
    7. 52
    Prev
    Next
    INDEX
    Explanations

    sections from legal and scientific publications, including signal phrases like "discussing", "note", "see", and citations

    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
     myſelf
    -1.14
     pleaſure
    -0.97
     itſelf
    -0.96
    ſelf
    -0.91
    parsedMessage
    -0.90
     Houſe
    -0.88
     photolibrary
    -0.87
     purpoſe
    -0.86
     Roskov
    -0.86
     faſt
    -0.85
    POSITIVE LOGITS
    <bos>
    1.99
     
    1.30
    '
    1.16
    ’
    1.10
    “
    1.00
    "
    0.98
    )
    0.93
    ).
    0.91
    [
    0.90
    ”
    0.90
    Activations Density 57.853%

    No Known Activations