© 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. 6786
    Prev
    Next
    INDEX
    Explanations

    patterns of structured symbols and formatting elements

    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
    zzini
    -0.63
    erno
    -0.63
     Champ
    -0.61
     Sim
    -0.60
    ан
    -0.60
    DMS
    -0.60
     Væ
    -0.57
     mimpi
    -0.57
    Sim
    -0.56
    symb
    -0.56
    POSITIVE LOGITS
               
    1.48
    +#+#
    1.09
     ویکی‌پدیا
    1.07
    IUrlHelper
    0.98
     дописавши
    0.96
     protoimpl
    0.91
     సౌకర్య
    0.91
     devriez
    0.88
     مواليد
    0.86
    TagMode
    0.85
    Activations Density 0.026%

    No Known Activations