© 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. 13813
    Prev
    Next
    INDEX
    Explanations

    references to a specific class of substances, particularly compounds like PCP, verapamil, and similar, often associated with drugs or pharmacology

    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
    ver
    -0.82
    VER
    -0.66
    verständlich
    -0.61
    verk
    -0.54
    quiera
    -0.52
     Horacio
    -0.52
     emper
    -0.50
     squash
    -0.50
     olvidar
    -0.50
     Breakers
    -0.50
    POSITIVE LOGITS
     ver
    2.36
     vers
    0.71
     '\\;'
    0.70
     numerus
    0.68
    setVerticalGroup
    0.67
    Datuak
    0.66
     kaarangay
    0.66
    Collectors
    0.65
    ()]
    0.63
     verle
    0.61
    Activations Density 0.000%

    No Known Activations