© 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. 2485
    Prev
    Next
    INDEX
    Explanations

    references to legal searches, warrants, and related judicial procedures

    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
    مساعدة
    -0.45
     humaine
    -0.40
     müş
    -0.39
    眨眼
    -0.38
     '\\;'
    -0.37
     consciência
    -0.35
     umane
    -0.35
    self
    -0.34
    ровок
    -0.34
     evidence
    -0.34
    POSITIVE LOGITS
    bootstrapcdn
    0.90
    TemporalType
    0.90
     كومونز
    0.89
     ostavi
    0.84
    npmjs
    0.80
     Himo
    0.79
    yarnpkg
    0.76
    tagext
    0.76
    ofire
    0.75
    ernalia
    0.75
    Activations Density 0.840%

    No Known Activations