© 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. 0-RES-MATRYOSHKA-DC
    7. 11925
    Prev
    Next
    INDEX
    Explanations

    mentions of specific pharmacological agents used as antagonists

    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
    tableFuture
    -0.87
     AssemblyProduct
    -0.86
    libft
    -0.79
    windigkeit
    -0.73
    HasAnnotation
    -0.72
     AssemblyCulture
    -0.72
    بوابة
    -0.70
    djangoproject
    -0.67
     ویکی‌پدیا
    -0.67
     StatefulWidget
    -0.67
    POSITIVE LOGITS
     antagonist
    2.72
     antagonists
    2.28
     antagon
    1.12
     antagonistic
    1.01
     antagonism
    0.95
     agonist
    0.94
    tagonist
    0.93
     protagonist
    0.89
     villain
    0.87
     protagonists
    0.67
    Activations Density 0.002%

    No Known Activations