© 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. 18-RES-MATRYOSHKA-DC
    7. 323
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to surgery

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     تضيفلها
    -0.75
    AndEndTag
    -0.62
    ModelAdmin
    -0.57
    UnitTesting
    -0.55
    archiviato
    -0.55
    EndContext
    -0.54
     незавершена
    -0.54
    TestingModule
    -0.54
     Exacts
    -0.53
     diarr
    -0.53
    POSITIVE LOGITS
     surgical
    1.08
     surgery
    0.98
     surgeons
    0.96
     Surgical
    0.95
    Surgical
    0.93
     Surgeons
    0.93
     Surgery
    0.92
     surgically
    0.91
    Surgery
    0.88
     surgeon
    0.88
    Activations Density 1.987%

    No Known Activations