© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94987
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -3.28
    themselves
    -3.08
     themſelves
    -2.23
     itself
    -2.22
    itself
    -2.14
     itſelf
    -2.13
     yourselves
    -1.91
     Itself
    -1.88
     herself
    -1.82
     himself
    -1.70
    POSITIVE LOGITS
    ,
    0.65
    .
    0.64
     a
    0.62
     in
    0.61
    ...
    0.60
    ix
    0.60
     -
    0.59
     i
    0.59
    e
    0.57
    '
    0.57
    Activations Density 0.027%

    No Known Activations