© 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. 13564
    Prev
    Next
    INDEX
    Explanations

    references to specific vascular structures, particularly the petrous segment of the internal carotid artery

    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
     ujednoznacz
    -0.57
     kasarigan
    -0.49
    indexing
    -0.49
    lossians
    -0.47
     asistir
    -0.47
    تفصیلات
    -0.47
     MessageBoxIcon
    -0.47
    quake
    -0.47
    chowy
    -0.47
     propOrder
    -0.47
    POSITIVE LOGITS
    tery
    4.13
    TERY
    1.95
    teries
    1.09
    teri
    0.68
     الحره
    0.66
    terie
    0.66
     buttery
    0.66
    teria
    0.65
    attery
    0.63
    tero
    0.62
    Activations Density 0.000%

    No Known Activations