© 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. 77341
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    RefNanny
    -0.84
     CreateTagHelper
    -0.63
    Einzelnachweise
    -0.58
    EndContext
    -0.55
     Administrativna
    -0.54
    ستار
    -0.52
    FieldBuilder
    -0.52
    下一篇
    -0.51
    IsContent
    -0.51
    vacy
    -0.49
    POSITIVE LOGITS
     disambiguazione
    0.56
     stanovnika
    0.49
     BoxDecoration
    0.49
     AssemblyTitle
    0.47
    zzi
    0.47
    uteen
    0.47
    zelf
    0.46
    tology
    0.45
    Pty
    0.44
    lección
    0.44
    Activations Density 0.000%

    No Known Activations