© 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-2-2B
    5. 5-CLT-HP
    7. 91183
    Prev
    Next
    INDEX
    Explanations

    group 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
    __':
    -0.65
     open
    -0.56
    ]^{-
    -0.56
     we
    -0.55
     wait
    -0.53
     *
    -0.52
    aniem
    -0.52
    castic
    -0.52
    ]+"
    -0.52
     par
    -0.52
    POSITIVE LOGITS
    .
    0.98
     and
    0.63
     militaires
    0.61
     lettore
    0.61
     vänner
    0.60
    voorbeeld
    0.60
     fournisseurs
    0.60
     alcuna
    0.59
     joueurs
    0.58
     spectateurs
    0.58
    Activations Density 0.001%

    No Known Activations