© 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. 20-CLT-HP
    7. 74814
    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
     vastaan
    -0.70
     المعيارى
    -0.69
     végétale
    -0.66
    Herb
    -0.65
     Extensions
    -0.60
    lograph
    -0.59
     Herb
    -0.59
     Petter
    -0.59
     PLANT
    -0.58
     Villages
    -0.58
    POSITIVE LOGITS
    Havolalar
    0.63
    her
    0.52
    stateProvider
    0.51
    djangoproject
    0.50
     Meksiku
    0.49
     للاسماء
    0.48
    GraphicsUnit
    0.47
    BagLayout
    0.46
    咙
    0.45
    MLLoader
    0.43
    Activations Density 0.001%

    No Known Activations