© 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. 256
    Prev
    Next
    INDEX
    Explanations

    references to governmental actions and policies regarding trade or sanctions

    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
     our
    -0.52
     your
    -0.48
     my
    -0.48
     disini
    -0.46
     (
    -0.46
     I
    -0.43
     you
    -0.42
     any
    -0.42
     maravillosa
    -0.42
    /
    -0.42
    POSITIVE LOGITS
     faſt
    0.90
     ſche
    0.84
     Majefty
    0.81
     محفوظة
    0.79
     queſta
    0.77
     Anſ
    0.77
     fubject
    0.76
     ſte
    0.75
    ſelf
    0.73
     fhort
    0.73
    Activations Density 4.748%

    No Known Activations