© 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. 195
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of uncertainty

    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
    RenderAtEndOf
    -0.60
    ideas
    -0.53
    SequentialGroup
    -0.50
    uride
    -0.47
    ValueStyle
    -0.47
     endwhile
    -0.47
    UDES
    -0.46
    riu
    -0.46
    roquia
    -0.46
     giusti
    -0.46
    POSITIVE LOGITS
     not
    1.02
     Not
    0.88
    not
    0.83
    Not
    0.79
     NOT
    0.78
     necessarily
    0.77
    Tidak
    0.74
     Nicht
    0.70
    NOT
    0.69
    Nicht
    0.68
    Activations Density 0.957%

    No Known Activations