© 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. 5-CLT-HP
    7. 94360
    Prev
    Next
    INDEX
    Explanations

    Increase, surge, or rapid growth

    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
     utafitiHapana
    -0.82
    +#+#
    -0.78
     nahilalakip
    -0.77
     désolés
    -0.72
     mourut
    -0.72
    //
    -0.69
    TypedDataSet
    -0.68
     Meksiku
    -0.68
    quelize
    -0.67
    OGND
    -0.65
    POSITIVE LOGITS
     of
    0.66
     moment
    0.55
     rise
    0.54
     among
    0.51
     return
    0.50
     unlike
    0.50
     effect
    0.50
     in
    0.49
     rush
    0.49
    TextWatcher
    0.49
    Activations Density 0.001%

    No Known Activations