© 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. 32011
    Prev
    Next
    INDEX
    Explanations

    references to specific types of tiles

    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
    Negative Logits
    ंदीखरीदारी
    -1.12
    IActionResult
    -0.93
     himo
    -0.90
    complexContent
    -0.89
     Eugenia
    -0.85
    цездатний
    -0.83
    prepareStatement
    -0.82
    webElementXpaths
    -0.82
    StructEnd
    -0.81
    InjectAttribute
    -0.79
    POSITIVE LOGITS
     tiles
    1.69
     tile
    1.64
     Tile
    1.61
    Tile
    1.45
     Tiles
    1.45
    tile
    1.38
    TILE
    1.38
    Tiles
    1.34
     TILE
    1.32
    tiles
    1.28
    Activations Density 0.005%

    No Known Activations