© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15448
    Prev
    Next
    INDEX
    Explanations

    references to chemical or biological agents, specifically focusing on the word "ro" which relates to "ro" like in "ro" from "ro" in medical or scientific terminology

    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
     Ro
    -1.17
    Ro
    -1.02
     ro
    -0.98
     RO
    -0.77
     متعلقه
    -0.69
    /***/
    -0.58
     rolo
    -0.57
    سطس
    -0.52
    катери
    -0.51
    \{\\
    -0.51
    POSITIVE LOGITS
    ro
    0.89
    numerusform
    0.71
     <>",
    0.67
    ChildIndex
    0.66
    rock
    0.65
    roek
    0.64
    roffen
    0.62
     siap
    0.59
    Espèce
    0.59
     TabLayout
    0.58
    Activations Density 0.002%

    No Known Activations