© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    references to legal filings, motions, and court procedural language

    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
    WaitGroup
    -0.77
     StringTokenizer
    -0.75
     AppComponent
    -0.68
     createStore
    -0.67
     "¿
    -0.67
     مرئيه
    -0.66
     BoxFit
    -0.66
    EndInit
    -0.65
     initWithFrame
    -0.64
    memoized
    -0.63
    POSITIVE LOGITS
     COVID
    0.58
     Covid
    0.52
    ırl
    0.50
     costs
    0.49
    ⓧ
    0.48
    brigens
    0.47
    исленность
    0.47
     kullanı
    0.44
    Drawable
    0.44
    время
    0.43
    Activations Density 0.842%

    No Known Activations