© 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. 77245
    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
    AndEndTag
    -0.84
     الحره
    -0.82
     '\\;'
    -0.81
     مشين
    -0.81
    Tembelea
    -0.77
     cref
    -0.76
     Meksiku
    -0.69
    expandindo
    -0.68
    twimg
    -0.65
    djangoproject
    -0.65
    POSITIVE LOGITS
    insee
    0.47
    Flg
    0.43
    ніципа
    0.41
     esternos
    0.39
    ುವ
    0.38
    csolódó
    0.38
     AutoMapper
    0.38
    が付いて
    0.37
    がついて
    0.37
    rouvez
    0.36
    Activations Density 0.000%

    No Known Activations