© 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. 15604
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups involved in investigations or accountability

    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
    endsection
    -0.54
     vilka
    -0.54
    UnusedPrivate
    -0.53
    ategy
    -0.51
    ViewHolder
    -0.50
    onViewCreated
    -0.49
     SearchView
    -0.49
    laient
    -0.49
     critic
    -0.48
     Monat
    -0.48
    POSITIVE LOGITS
     prosecutors
    1.13
     regulators
    1.05
     investigators
    0.96
     authorities
    0.88
     officials
    0.88
     وتسجيلات
    0.88
     archaeologists
    0.87
     organizers
    0.87
     scientists
    0.86
     historians
    0.86
    Activations Density 0.035%

    No Known Activations