© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26596
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and injuries, particularly related to trauma and surgery

    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
    WebpackPlugin
    -0.62
    estacks
    -0.57
     mergeFrom
    -0.51
     Вікі
    -0.48
    cvtColor
    -0.44
     CHtml
    -0.44
     gran
    -0.44
    CreateModel
    -0.43
    ochrom
    -0.42
    RestTemplate
    -0.40
    POSITIVE LOGITS
     חיצוניים
    0.73
    الحياه
    0.70
    Personendaten
    0.68
     kaarangay
    0.66
     متعلقه
    0.64
     relâche
    0.64
    AddTagHelper
    0.63
    harusnya
    0.61
    ⓧ
    0.60
     سكانية
    0.60
    Activations Density 0.141%

    No Known Activations