© 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. 40644
    Prev
    Next
    INDEX
    Explanations

    newborns

    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
    ricle
    -0.92
    ibel
    -0.72
    ValueStyle
    -0.71
     الرياضيه
    -0.67
    bele
    -0.59
    AnchorTagHelper
    -0.58
    lame
    -0.56
     Lame
    -0.55
     lame
    -0.52
     otomatig
    -0.50
    POSITIVE LOGITS
    ுக்கு
    0.60
     internetowa
    0.58
    ecore
    0.57
     Prze
    0.54
     Merdeka
    0.54
     mAdapter
    0.53
     joaat
    0.52
    TestingModule
    0.52
    ">//
    0.52
    tray
    0.51
    Activations Density 1.574%

    No Known Activations