© 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. 40287
    Prev
    Next
    INDEX
    Explanations

    thinking

    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
    He
    -0.53
    off
    -0.52
    made
    -0.51
    糙
    -0.48
    then
    -0.47
    out
    -0.47
    ’
    -0.47
    ם
    -0.47
    Hi
    -0.46
     off
    -0.45
    POSITIVE LOGITS
     autorytatywna
    1.15
    gameserver
    1.02
     disambiguazione
    0.97
    ⓧ
    0.94
    queryInterface
    0.92
     resourceCulture
    0.89
    MLLoader
    0.82
    NameInMap
    0.81
    GEBURTSDATUM
    0.81
     onCancelled
    0.80
    Activations Density 0.272%

    No Known Activations