© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13414
    Prev
    Next
    INDEX
    Explanations

    references to legal rules, statutes, or regulations

    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
     civiles
    -0.66
     civilian
    -0.65
     civil
    -0.64
    ætte
    -0.61
    TemporalType
    -0.57
     @"/
    -0.56
     judiciales
    -0.54
     civilians
    -0.54
     Tro
    -0.53
    fony
    -0.53
    POSITIVE LOGITS
     Civil
    1.91
    Civil
    1.25
     CIVIL
    0.77
     Confederate
    0.59
     תפ
    0.57
     مشين
    0.56
     Revolutionary
    0.55
     Napoleonic
    0.55
     ujednoznacz
    0.54
     Union
    0.54
    Activations Density 0.002%

    No Known Activations