© 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. 96327
    Prev
    Next
    INDEX
    Explanations

    surprise events

    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
     tertinggi
    -0.59
     rangs
    -0.55
    μβρίου
    -0.53
    selves
    -0.51
    Filmo
    -0.51
    PRNewswire
    -0.50
     revés
    -0.50
     totalidad
    -0.50
     arranque
    -0.50
     trovano
    -0.50
    POSITIVE LOGITS
    WebVitals
    0.71
     many
    0.64
     anyone
    0.62
    WithIOException
    0.60
    '][$
    0.57
    ()][
    0.57
    jsonwebtoken
    0.57
    ')[
    0.57
     you
    0.57
     long
    0.55
    Activations Density 0.001%

    No Known Activations