© 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. 2-RES-MATRYOSHKA-DC
    7. 5430
    Prev
    Next
    INDEX
    Explanations

    patterns of formatting and structural markers in text, such as borders, separators, or repeated symbols

    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
    PRNewswire
    -0.92
    --------------
    -0.84
     Roskov
    -0.82
    +#+#
    -0.79
    ------
    -0.78
    BagConstraints
    -0.77
    EndInit
    -0.75
    RetentionPolicy
    -0.75
    principalColumn
    -0.75
    Batis
    -0.75
    POSITIVE LOGITS
     ----------
    0.52
     --------------
    0.52
     ---------
    0.48
     rač
    0.47
    告
    0.44
    xiety
    0.44
     nødvendig
    0.43
    کز
    0.43
    و
    0.43
     place
    0.42
    Activations Density 0.050%

    No Known Activations