© 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. 1-RES-MATRYOSHKA-DC
    7. 1268
    Prev
    Next
    INDEX
    Explanations

    examples related to technical specifications and descriptions of engineered methods or devices

    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
    <eos>
    -0.78
    .
    -0.76
    ,
    -0.63
     so
    -0.61
     various
    -0.60
    /
    -0.59
    -
    -0.57
     as
    -0.57
    '
    -0.56
     also
    -0.55
    POSITIVE LOGITS
    WebVitals
    1.02
     photolibrary
    1.02
     utafitiHapana
    0.93
     '\\;'
    0.87
    ^(@)
    0.82
     myſelf
    0.82
    adə
    0.80
    WebServlet
    0.78
     ſind
    0.77
    >\<^
    0.77
    Activations Density 10.490%

    No Known Activations