© 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. 71
    Prev
    Next
    INDEX
    Explanations

    references to arrogance and self-importance in a critical context

    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
     następnie
    -0.65
     также
    -0.64
     ilustracja
    -0.63
     conformément
    -0.63
     operations
    -0.60
     również
    -0.60
     obszar
    -0.59
     utilização
    -0.59
     posky
    -0.59
     lecz
    -0.59
    POSITIVE LOGITS
     fucking
    0.86
     freaking
    0.86
     stuff
    0.79
     freakin
    0.79
     goddamn
    0.78
     fuckin
    0.78
     damn
    0.77
     stupid
    0.77
     shitty
    0.77
     crazy
    0.76
    Activations Density 15.889%

    No Known Activations