© 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. 42679
    Prev
    Next
    INDEX
    Explanations

    Words ending in "ries/ras"

    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
    ries
    -1.57
    ras
    -1.14
    ced
    -1.04
    ged
    -1.04
    rie
    -0.93
    RIES
    -0.83
    ried
    -0.80
    cies
    -0.80
    RIED
    -0.77
    RIE
    -0.73
    POSITIVE LOGITS
     Waray
    0.79
    MessageOf
    0.78
    ValueStyle
    0.75
     LEYENDO
    0.75
     للاسماء
    0.69
     tartalomajánló
    0.68
     Lightboxes
    0.64
    Personensuche
    0.64
     correctes
    0.62
    Personendaten
    0.62
    Activations Density 0.024%

    No Known Activations