© 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. 278
    Prev
    Next
    INDEX
    Explanations

    collective pronouns and phrases related to shared experiences or actions

    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
     himself
    -0.50
     Itself
    -0.46
     itself
    -0.45
    himself
    -0.43
     herself
    -0.42
    本身
    -0.40
     Its
    -0.40
     its
    -0.39
     his
    -0.38
    Its
    -0.37
    POSITIVE LOGITS
     ourselves
    1.11
    We
    0.93
     we
    0.89
     We
    0.84
     เรา
    0.81
     máme
    0.81
     우리
    0.80
     our
    0.78
     jsme
    0.77
    我們
    0.75
    Activations Density 1.623%

    No Known Activations