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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5710
    Prev
    Next
    INDEX
    Explanations

    factual information and references to case facts in documents

    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
     fact
    -0.93
     nahilalakip
    -0.71
    fact
    -0.63
     Tatsache
    -0.60
    tamment
    -0.57
     hecho
    -0.55
    RegistryLite
    -0.54
     typename
    -0.53
     presenza
    -0.52
    näm
    -0.52
    POSITIVE LOGITS
     facts
    2.02
     Facts
    1.63
    facts
    1.62
     FACTS
    1.56
    Facts
    1.40
    FACTS
    1.24
     Fakten
    1.05
     factual
    0.91
     fatos
    0.89
     факты
    0.88
    Activations Density 0.012%

    No Known Activations