© 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. 11913
    Prev
    Next
    INDEX
    Explanations

    references to drug dosage or treatment protocols

    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
     Or
    -0.89
    Or
    -0.87
    OR
    -0.72
     onOptions
    -0.66
    Orm
    -0.62
    Ор
    -0.62
    or
    -0.60
    orm
    -0.59
     ор
    -0.57
     OR
    -0.56
    POSITIVE LOGITS
     eller
    2.59
     oder
    1.63
     vagy
    1.55
     alebo
    1.55
     nebo
    1.42
    Eller
    1.34
     või
    1.27
     veya
    1.23
     atau
    1.07
     Eller
    1.04
    Activations Density 0.000%

    No Known Activations