© 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. 1641
    Prev
    Next
    INDEX
    Explanations

    pectin

    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
     pectin
    -1.21
     Monfieur
    -0.89
    race
    -0.85
     Efq
    -0.84
     pect
    -0.80
     Inſ
    -0.79
     Anſ
    -0.78
     Majefty
    -0.78
     uſed
    -0.77
     Eſ
    -0.76
    POSITIVE LOGITS
    ItemSelected
    0.48
    diyesi
    0.48
     оригіналу
    0.48
     man
    0.47
     flu
    0.46
     MAN
    0.46
     h
    0.46
    Климат
    0.46
    igera
    0.46
    initComponents
    0.46
    Activations Density 0.573%

    No Known Activations