© 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. 6674
    Prev
    Next
    INDEX
    Explanations

    references to funding and financial support

    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
     Pater
    -0.82
    reci
    -0.71
     ASR
    -0.70
     Merle
    -0.70
     وتسجيلات
    -0.68
     McLaughlin
    -0.68
     attra
    -0.68
    vle
    -0.68
     Mahesh
    -0.67
     Agre
    -0.67
    POSITIVE LOGITS
    Funds
    1.36
     FUND
    1.34
     Fund
    1.30
     Funds
    1.30
     fund
    1.28
     funding
    1.27
     Funding
    1.27
    FUNDING
    1.27
    funding
    1.26
    funds
    1.25
    Activations Density 0.020%

    No Known Activations