© 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. 5-CLT-HP
    7. 91317
    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
     a
    -0.65
     the
    -0.49
    хіво
    -0.49
     dotato
    -0.48
     an
    -0.48
     without
    -0.48
     vastaan
    -0.48
     endast
    -0.48
     yalnızca
    -0.48
     such
    -0.47
    POSITIVE LOGITS
     eminence
    0.62
    MemoryWarning
    0.60
    Sucesor
    0.59
    coration
    0.58
     كومونز
    0.58
     FetchType
    0.57
     cherchés
    0.57
    fillType
    0.57
    barrow
    0.56
     Photocase
    0.54
    Activations Density 0.003%

    No Known Activations