© 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. 15666
    Prev
    Next
    INDEX
    Explanations

    the neuron is looking for references to specific dosing regimens or dosages

    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
    untung
    -0.68
    didSet
    -0.57
    gever
    -0.56
     colpo
    -0.56
    iquest
    -0.52
    πού
    -0.52
    hirts
    -0.51
    actéristique
    -0.50
     Loaf
    -0.50
    gewä
    -0.50
    POSITIVE LOGITS
     dosing
    2.61
    تقاوى
    0.99
     مرئيه
    0.72
    참고
    0.68
     })}
    0.67
    osing
    0.63
    XmlAccessType
    0.61
     JD
    0.59
     DOS
    0.59
    JD
    0.57
    Activations Density 0.001%

    No Known Activations