© 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. 6222
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or organizations

    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
    RenderAtEndOf
    -0.77
     UIFont
    -0.71
    #+#
    -0.63
     BoxDecoration
    -0.58
    tagHelper
    -0.56
    ToBounds
    -0.54
    useEffect
    -0.54
     NSCoder
    -0.54
     endforeach
    -0.53
    IntoConstraints
    -0.53
    POSITIVE LOGITS
     damaligen
    0.59
     inför
    0.53
    当时的
    0.53
     damals
    0.52
     now
    0.52
    /
    0.51
    當時
    0.50
     then
    0.49
     transformed
    0.49
    MessageOf
    0.49
    Activations Density 0.398%

    No Known Activations