© 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. 2-RES-MATRYOSHKA-DC
    7. 7678
    Prev
    Next
    INDEX
    Explanations

    words related to legal citations or references

    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
    Negative Logits
    MessageOf
    -0.63
    цездатний
    -0.61
     autorytatywna
    -0.61
     ExecuteAsync
    -0.60
    IsMutable
    -0.56
     oublié
    -0.54
     dataSnapshot
    -0.52
    ItemBackground
    -0.51
    ValueGenerated
    -0.51
     internetowa
    -0.50
    POSITIVE LOGITS
    rog
    3.97
    ROG
    2.23
    rogation
    1.86
    rogate
    1.52
    rogates
    1.38
    roga
    1.30
     rog
    1.21
    Rog
    1.13
     Rog
    1.04
    rogen
    0.94
    Activations Density 0.002%

    No Known Activations