© 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. 3-RES-MATRYOSHKA-DC
    7. 3314
    Prev
    Next
    INDEX
    Explanations

    words that indicate legal issues, often in the context of a court case

    oai_token-act-pair · gemini-2.0-flash
    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
     Magellan
    -0.54
    preventDefault
    -0.50
    Сюжет
    -0.50
    HomeAsUpEnabled
    -0.48
     AnyObject
    -0.47
    putin
    -0.47
     Picchu
    -0.47
    cendental
    -0.47
    rentino
    -0.47
    ματα
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.78
    ClCompile
    0.75
    发表于
    0.71
    ReusableCell
    0.70
     snippetHide
    0.69
    Hentet
    0.66
     ProtoMessage
    0.64
     становника
    0.63
    idł
    0.61
    EndGlobalSection
    0.60
    Activations Density 0.313%

    No Known Activations