© 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. 20-CLT-HP
    7. 76469
    Prev
    Next
    INDEX
    Explanations

    language morphology

    np_max-act-logits · 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
    ieteur
    -0.49
    期刊论文
    -0.49
     initComponents
    -0.49
     intptr
    -0.49
    ooker
    -0.48
    QSize
    -0.47
    出版年
    -0.46
    Abitanti
    -0.46
    CDCl
    -0.45
    enumi
    -0.45
    POSITIVE LOGITS
     morphology
    0.82
     morphe
    0.82
     prefixes
    0.74
     morphological
    0.68
     morpho
    0.68
     phon
    0.67
     morfo
    0.66
     cogn
    0.66
     roots
    0.65
     conjugation
    0.65
    Activations Density 0.003%

    No Known Activations