© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 198
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or components in a structured context

    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
     estekak
    -0.67
     utafitiHapana
    -0.64
     مفص
    -0.61
    يكب
    -0.53
     Arach
    -0.52
     Biôgrafia
    -0.52
    Joh
    -0.52
    errHandler
    -0.52
    anam
    -0.50
    Tembelea
    -0.49
    POSITIVE LOGITS
     Exacts
    0.72
    TagMode
    0.67
    GeoNames
    0.64
    ChildScrollView
    0.60
    Zeneca
    0.60
    rrggbb
    0.58
    adget
    0.57
     CreateTagHelper
    0.56
    MigrationBuilder
    0.55
    AndEndTag
    0.54
    Activations Density 0.992%

    No Known Activations