© 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. 12368
    Prev
    Next
    INDEX
    Explanations

    mentions of the Latin-derived term for a medicinal plant, specifically 'cannula'

    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
    ules
    -0.99
    ulo
    -0.98
    ulus
    -0.74
    ulate
    -0.73
    ULE
    -0.68
    ule
    -0.67
    ULES
    -0.63
    ULO
    -0.60
    ulating
    -0.60
    +#+
    -0.60
    POSITIVE LOGITS
    ula
    2.20
    ULA
    1.44
    ulae
    0.80
    Richard
    0.57
     Richard
    0.56
    actin
    0.56
     rocker
    0.55
    ที่ยว
    0.55
    ковь
    0.54
     Rabin
    0.54
    Activations Density 0.001%

    No Known Activations