© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 749
    Prev
    Next
    INDEX
    Explanations

    references to health insurance coverage, particularly focusing on mentions of insurance plans, Obamacare, and related coverage terms

    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
     Administrativna
    -0.71
     McQu
    -0.67
    раздо
    -0.54
     jScrollPane
    -0.54
    écart
    -0.53
     Devan
    -0.52
    пать
    -0.52
    chargez
    -0.52
     Arund
    -0.50
     echip
    -0.50
    POSITIVE LOGITS
     insurance
    3.92
     Insurance
    3.61
    Insurance
    3.53
    insurance
    3.50
     INSURANCE
    3.41
     insured
    3.28
     insurers
    2.97
    insured
    2.89
     insur
    2.84
     insure
    2.78
    Activations Density 0.204%

    No Known Activations