© 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. 1-RES-MATRYOSHKA-DC
    7. 1207
    Prev
    Next
    INDEX
    Explanations

    references to specific comparisons or the act of comparing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.91
     propOrder
    -0.88
     Kom
    -0.83
    rungsseite
    -0.82
     pinulongan
    -0.74
    smithy
    -0.73
     &___
    -0.72
    Kom
    -0.72
     kom
    -0.71
    comp
    -0.69
    POSITIVE LOGITS
     compared
    4.16
    compared
    3.59
     Compared
    3.19
    Compared
    3.06
     dibandingkan
    2.44
     compare
    2.30
     compares
    2.22
     сравнению
    1.98
     Compare
    1.98
     comparación
    1.96
    Activations Density 0.211%

    No Known Activations