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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15250
    Prev
    Next
    INDEX
    Explanations

    the presence of specific Cyrillic characters, likely parts of a particular word or phrase in Russian

    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
    ChildScrollView
    -0.57
    արտ
    -0.50
    )|^{
    -0.48
    ดา
    -0.47
    ]='\
    -0.47
    brück
    -0.47
     оригіналу
    -0.47
    τισ
    -0.46
     mı
    -0.46
    ercice
    -0.45
    POSITIVE LOGITS
    л
    3.34
    Л
    1.45
    лл
    0.96
    ла
    0.87
    лло
    0.86
     л
    0.85
     متعلقه
    0.83
    лля
    0.83
    ł
    0.82
    лд
    0.80
    Activations Density 0.000%

    No Known Activations