© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 84
    Prev
    Next
    INDEX
    Explanations

    citations of legal cases or references to legal terminology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    RenderAtEndOf
    -0.82
     متعلقه
    -0.70
    <unused23>
    -0.65
    <unused73>
    -0.65
    <unused79>
    -0.65
    
    -0.65
    <unused8>
    -0.65
    <unused14>
    -0.65
    <unused16>
    -0.65
    <unused32>
    -0.65
    POSITIVE LOGITS
    Rptr
    0.55
     reported
    0.50
    reported
    0.47
     Rptr
    0.43
     recently
    0.36
     cited
    0.35
    aujourd
    0.33
     unpublished
    0.32
     failed
    0.32
     published
    0.31
    Activations Density 2.800%

    No Known Activations