© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15631
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name, indicating it is focused on identifying mentions or discussions of a particular individual

    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
     utafitiHapana
    -0.59
    cVar
    -0.56
     незавершена
    -0.56
     للاسماء
    -0.54
     noqa
    -0.53
    XMLSchema
    -0.52
    viedo
    -0.52
    цездатний
    -0.51
    InteropServices
    -0.50
    tiously
    -0.50
    POSITIVE LOGITS
     Dean
    3.30
    Dean
    3.17
     DEAN
    2.72
     dean
    2.70
    DEAN
    2.06
    dean
    1.73
     Deans
    1.69
     Deane
    0.77
     Dino
    0.59
     Supernatural
    0.54
    Activations Density 0.001%

    No Known Activations