© 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. 0-RES-MATRYOSHKA-DC
    7. 10564
    Prev
    Next
    INDEX
    Explanations

    references to covalent chemical bonds or linkages in scientific text

    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
     незавершена
    -0.77
    DoubleQuotes
    -0.66
    instancetype
    -0.59
     angekommen
    -0.54
    amssymb
    -0.52
     början
    -0.51
    놨
    -0.50
     erv
    -0.50
    baselines
    -0.50
    כז
    -0.49
    POSITIVE LOGITS
    用
    2.45
     covalent
    1.95
     用
    1.75
    用の
    1.38
    用的
    1.26
    用了
    1.11
    用に
    1.07
    용
    1.03
    用水
    1.02
    用手
    1.00
    Activations Density 0.000%

    No Known Activations