© 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. 2-RES-MATRYOSHKA-DC
    7. 2407
    Prev
    Next
    INDEX
    Explanations

    references to the gap or energy gap in scientific contexts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     semblables
    -0.61
    #+#
    -0.60
     lubang
    -0.60
    AlterField
    -0.59
     bors
    -0.59
     économies
    -0.55
     perforated
    -0.54
    popularity
    -0.54
     assin
    -0.54
     autorisés
    -0.54
    POSITIVE LOGITS
     gap
    3.34
     Gap
    3.09
    gap
    2.94
    Gap
    2.83
     gaps
    2.66
     Gaps
    2.55
    gaps
    2.36
     GAP
    1.99
    GAP
    1.83
    갭
    1.32
    Activations Density 0.009%

    No Known Activations