© 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. 21
    Prev
    Next
    INDEX
    Explanations

    references to individuals and pronouns in a narrative or discussion

    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
     of
    -0.39
    ,
    -0.35
     Pos
    -0.32
     Bos
    -0.31
    fromLTRB
    -0.30
    덟
    -0.30
     Common
    -0.30
     Gay
    -0.30
     foreign
    -0.29
     Natural
    -0.29
    POSITIVE LOGITS
    Mereka
    1.09
     Ellos
    1.06
    they
    1.04
    They
    1.02
     Mereka
    1.00
    Они
    0.98
    THEY
    0.97
     they
    0.93
     ſind
    0.93
     mereka
    0.93
    Activations Density 4.427%

    No Known Activations