© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12995
    Prev
    Next
    INDEX
    Explanations

    references to turmeric and cumin, indicating it's looking for mentions of these medicinal herbs and their components

    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
    iotti
    -0.65
    ')):
    -0.60
     }}</
    -0.59
    atown
    -0.58
     porn
    -0.57
    ladel
    -0.56
    sphase
    -0.55
    nict
    -0.55
     pornography
    -0.54
     Adamson
    -0.52
    POSITIVE LOGITS
    cumin
    1.70
    hoc
    0.90
     ESP
    0.90
    ESP
    0.83
    rost
    0.82
     تضيفلها
    0.80
    ValueStyle
    0.73
     gynhyrchwyd
    0.70
    farin
    0.70
    maan
    0.65
    Activations Density 0.006%

    No Known Activations