© 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. 892
    Prev
    Next
    INDEX
    Explanations

    order

    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
    complexContent
    -0.62
    ValueGeneration
    -0.61
    makeConstraints
    -0.60
    ConstraintMaker
    -0.60
    кономі
    -0.59
    SourceChecksum
    -0.58
     Numerade
    -0.57
     estimés
    -0.57
    intios
    -0.56
    TestTools
    -0.56
    POSITIVE LOGITS
     of
    0.59
     naturelle
    0.52
    Lähteet
    0.51
    üme
    0.50
     šķ
    0.49
     sopra
    0.49
     пожалуйста
    0.49
     generales
    0.48
     Serious
    0.48
    MENAFN
    0.47
    Activations Density 0.001%

    No Known Activations