© 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. 30626
    Prev
    Next
    INDEX
    Explanations

    references to structural components in a layout or design 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
    Negative Logits
    ModelAdmin
    -0.88
    #+#
    -0.87
     שוליים
    -0.82
     ExecuteAsync
    -0.80
     ModelAndView
    -0.76
    stateProvider
    -0.76
    Jaz
    -0.74
    MediaStore
    -0.74
    Skocz
    -0.72
    y
    -0.70
    POSITIVE LOGITS
     bottom
    1.07
     Bottom
    1.03
    bottom
    0.98
     BOTTOM
    0.97
    Bottom
    0.93
     bottoms
    0.88
     botto
    0.88
    BOTTOM
    0.87
    truth
    0.77
     remer
    0.73
    Activations Density 0.015%

    No Known Activations