© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26720
    Prev
    Next
    INDEX
    Explanations

    terms related to vessels and their usage in medical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maury
    -0.96
    CreateMap
    -0.87
     dandy
    -0.83
     noDo
    -0.81
     fhort
    -0.78
     pleaſure
    -0.73
    quake
    -0.72
     Ramona
    -0.72
     leſs
    -0.72
    Vern
    -0.71
    POSITIVE LOGITS
     vessels
    1.52
     Vessels
    1.36
     vessel
    1.34
    vessel
    1.34
    Vessel
    1.33
     Vessel
    1.30
    vessels
    1.23
    Ves
    1.17
     ves
    0.97
     Ves
    0.96
    Activations Density 0.003%

    No Known Activations