© 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. 10420
    Prev
    Next
    INDEX
    Explanations

    references to legal principles or standards related to the burden of proof and the strength of evidence in judicial proceedings

    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
     morte
    -0.57
     life
    -0.54
     lives
    -0.54
    hardt
    -0.53
     Kaufmann
    -0.52
    ゴリー
    -0.49
     gyven
    -0.49
     bağlantılar
    -0.48
    Vida
    -0.47
     TextFormField
    -0.47
    POSITIVE LOGITS
     prevail
    3.41
     prevailed
    3.22
     prevails
    2.84
     prevailing
    1.41
     preva
    1.01
     PREV
    0.94
     triumphed
    0.84
    vailing
    0.77
     Wikimedijinoj
    0.76
     reigned
    0.75
    Activations Density 0.002%

    No Known Activations