© 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. 0-RES-MATRYOSHKA-DC
    7. 11539
    Prev
    Next
    INDEX
    Explanations

    CDATA sections containing numeric values, especially those with high activation levels, indicating it is detecting specific tagged data elements or structured information within 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
     חיצוניים
    -0.65
    FILES
    -0.63
     Waray
    -0.60
    ]")]
    -0.58
    ########.
    -0.58
     Kirkpatrick
    -0.57
    GraphicsUnit
    -0.57
     Gaj
    -0.57
    multer
    -0.56
    LayoutStyle
    -0.56
    POSITIVE LOGITS
    hysema
    0.75
    migrationBuilder
    0.71
     ContentValues
    0.70
    WritableDatabase
    0.68
    glClear
    0.67
    delser
    0.66
     ProtoMessage
    0.65
    LinkId
    0.64
     ViewPager
    0.59
    toare
    0.57
    Activations Density 0.078%

    No Known Activations