© 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. 22304
    Prev
    Next
    INDEX
    Explanations

    references to the Yang-Mills theory in theoretical physics

    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
     Slovak
    -0.79
    CodeDom
    -0.79
    #
    -0.76
     réfugi
    -0.75
     Vickers
    -0.74
    +#+#
    -0.72
     Prow
    -0.72
    Bli
    -0.72
     Centa
    -0.71
     stiefel
    -0.71
    POSITIVE LOGITS
     Yang
    1.77
    Yang
    1.57
     YANG
    1.40
    yang
    1.38
     yang
    1.04
     杨
    0.84
    NegativeButton
    0.77
    楊
    0.76
    杨
    0.75
    ||}
    0.71
    Activations Density 0.002%

    No Known Activations