© 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. 13596
    Prev
    Next
    INDEX
    Explanations

    references to citizenship status or classification

    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
    Citizens
    -0.75
     citizens
    -0.63
     Citizens
    -0.58
    citizens
    -0.54
    LEADING
    -0.52
    urf
    -0.49
    istic
    -0.48
     Secund
    -0.48
     '\\;'
    -0.48
    TAGS
    -0.45
    POSITIVE LOGITS
     citizen
    2.03
    citizen
    1.80
    Citizen
    1.79
     Citizen
    1.72
    ValueStyle
    0.83
     viewType
    0.71
    yntaxException
    0.71
    IZEN
    0.69
     étudiant
    0.65
    amateur
    0.63
    Activations Density 0.003%

    No Known Activations