© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3592
    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
     énergé
    -0.93
     définiti
    -0.90
     réguli
    -0.90
     démocr
    -0.85
     électroniques
    -0.84
     médicaux
    -0.84
     térm
    -0.82
     quelcon
    -0.82
     vectorielles
    -0.81
     normaux
    -0.79
    POSITIVE LOGITS
     will
    0.88
     is
    0.84
     can
    0.82
     are
    0.77
     must
    0.75
     may
    0.70
     could
    0.69
     would
    0.68
     has
    0.68
     have
    0.65
    Activations Density 0.002%

    No Known Activations