© 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. 2700
    Prev
    Next
    INDEX
    Explanations

    all

    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
    يكب
    -0.60
     numberOfRows
    -0.59
     Públicas
    -0.50
     suprême
    -0.48
    InSection
    -0.47
    CurrentValue
    -0.47
     інших
    -0.46
     whoſe
    -0.45
    retired
    -0.45
    cần
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.69
    ="@+
    0.68
     anymore
    0.67
    Referències
    0.61
     intptr
    0.57
     nakalista
    0.57
     skimage
    0.54
     <<<<<<<<<<<<<<
    0.53
     Winaray
    0.52
     שוליים
    0.52
    Activations Density 0.002%

    No Known Activations