© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43749
    Prev
    Next
    INDEX
    Explanations

    less

    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
     less
    -0.88
     weniger
    -0.66
     menos
    -0.62
     mindre
    -0.60
     менее
    -0.60
     fewer
    -0.59
     меньше
    -0.58
    Less
    -0.56
     moins
    -0.51
     Less
    -0.50
    POSITIVE LOGITS
     AspNetCore
    0.98
     مرئيه
    0.90
    Obrázky
    0.88
    SharedDtor
    0.85
    AnimationsModule
    0.85
     Chwiliwch
    0.84
    Legături
    0.81
    '},
    0.81
    PerformLayout
    0.80
    yntaxException
    0.80
    Activations Density 0.496%

    No Known Activations