© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12639
    Prev
    Next
    INDEX
    Explanations

    specific textual patterns or symbols typically used in scientific or technical documents, such as numerical data, measurement annotations, or formula components

    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
     abſ
    -0.69
     uſed
    -0.68
     uſe
    -0.68
     myſelf
    -0.68
    */),
    -0.67
    !")
    -0.66
     Roskov
    -0.66
     Houſe
    -0.66
    addPreferredGap
    -0.66
     houſe
    -0.66
    POSITIVE LOGITS
    }\]
    2.86
    %\]
    2.61
     \]
    1.78
    %\[
    0.75
    \]
    0.73
    %$$
    0.59
    ценка
    0.56
    PopupWindow
    0.55
    numerusform
    0.53
    anlagen
    0.52
    Activations Density 0.001%

    No Known Activations