© 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. 856
    Prev
    Next
    INDEX
    Explanations

    references to substances related to pharmaceuticals or drugs

    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
     Lightboxes
    -0.60
    calipsis
    -0.59
    énario
    -0.56
     cathédrale
    -0.54
    html
    -0.53
     Dishwasher
    -0.53
    calypse
    -0.52
     DeSantis
    -0.52
     MonoBehaviour
    -0.51
     lympho
    -0.51
    POSITIVE LOGITS
     drug
    4.22
     Drug
    3.73
     drugs
    3.72
    drug
    3.70
    Drug
    3.63
     DRUG
    3.41
     Drugs
    3.38
    drugs
    3.23
    Drugs
    3.22
     drogas
    2.27
    Activations Density 0.341%

    No Known Activations