© 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. 106
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to conviction and reversal processes in the context of criminal law

    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
     فريبيس
    -0.70
    Gön
    -0.69
    OGND
    -0.66
     Administrativna
    -0.66
    ⦊
    -0.64
    
    -0.64
     الرياضيه
    -0.63
    ⟬
    -0.63
     AssemblyCulture
    -0.62
     للمعارف
    -0.62
    POSITIVE LOGITS
     CURIAM
    0.53
    AFFIRMED
    0.37
    IContainer
    0.33
     argued
    0.31
    led
    0.29
     decidiu
    0.28
     Anordnung
    0.28
     Judge
    0.27
     pursuant
    0.27
     juges
    0.26
    Activations Density 5.615%

    No Known Activations