Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 8481
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging techniques, particularly related to chest scans and radiographs

    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
    ValueStyle
    -1.01
     يتيمه
    -0.99
    expandindo
    -0.94
    ArgsConstructor
    -0.78
    SourceChecksum
    -0.77
     propOrder
    -0.75
     IBOutlet
    -0.72
    setViewportView
    -0.70
    WebElementEntity
    -0.70
     initComponents
    -0.67
    POSITIVE LOGITS
    Structure
    0.51
     '[
    0.47
    Action
    0.47
     structure
    0.47
     Action
    0.46
     σχέ
    0.45
     action
    0.43
    structure
    0.43
     مدار
    0.41
     "
    0.41
    Activations Density 0.024%

    No Known Activations