© 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. 219
    Prev
    Next
    INDEX
    Explanations

    references to ownership and possessive pronouns

    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
     uſed
    -0.60
    jalá
    -0.55
     kobieta
    -0.52
     ſtate
    -0.52
    DataLoader
    -0.51
     myſelf
    -0.51
    SequentialGroup
    -0.50
     juſ
    -0.49
     uſe
    -0.49
     kvinnor
    -0.48
    POSITIVE LOGITS
     own
    1.22
     his
    0.89
    自己的
    0.88
     ihrer
    0.87
     their
    0.86
     자신의
    0.84
     His
    0.84
     Their
    0.84
     THEIR
    0.81
     kanyang
    0.81
    Activations Density 2.805%

    No Known Activations