© 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. 4-CLT-HP
    7. 2235
    Prev
    Next
    INDEX
    Explanations

    encourage

    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
    ₁)
    -0.52
    逅
    -0.49
    %%\
    -0.48
    ucoup
    -0.48
     presently
    -0.47
     tewas
    -0.46
     $*$
    -0.46
     with
    -0.46
     disponibilités
    -0.46
    ,
    -0.45
    POSITIVE LOGITS
    
    0.75
    contentLoaded
    0.70
     ويكيميديا
    0.69
    memoized
    0.62
     تضيفلها
    0.62
    MethodManager
    0.60
     contextLoads
    0.60
     anyone
    0.58
    ($__
    0.58
    RTGC
    0.56
    Activations Density 0.006%

    No Known Activations