© 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. 77500
    Prev
    Next
    INDEX
    Explanations

    technical and 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
    Попис
    -0.59
     FISHER
    -0.43
    Classe
    -0.42
    Looks
    -0.42
     مشين
    -0.42
    looks
    -0.42
    ста
    -0.41
    кот
    -0.41
    μβρίου
    -0.41
    Fisher
    -0.41
    POSITIVE LOGITS
    Referències
    0.75
     الحره
    0.74
    Datuak
    0.67
     jScrollPane
    0.65
    úcia
    0.62
     gynnwys
    0.54
     Infór
    0.54
    DispatchToProps
    0.53
     CommonModule
    0.52
     Seeder
    0.52
    Activations Density 0.000%

    No Known Activations