© 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. 434
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to employment and tax regulations

    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
    Negative Logits
     nuanced
    -0.46
     hinting
    -0.46
     downright
    -0.44
     hype
    -0.44
     horrible
    -0.43
     nasty
    -0.43
     hinted
    -0.43
     half
    -0.43
     whack
    -0.42
     squ
    -0.42
    POSITIVE LOGITS
     ſind
    0.69
     ModelExpression
    0.61
     uſe
    0.60
     ſhall
    0.58
     reaſon
    0.58
     BorderSide
    0.56
     activiteiten
    0.56
     preſent
    0.56
     purpoſe
    0.56
    ſelves
    0.55
    Activations Density 2.540%

    No Known Activations