© 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. 2328
    Prev
    Next
    INDEX
    Explanations

    months

    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
    WebElementEntity
    -0.73
    ograd
    -0.60
     nahilalakip
    -0.60
     Sylvain
    -0.59
    licata
    -0.57
     незавершена
    -0.57
     Mongols
    -0.57
    žiai
    -0.56
     Cassini
    -0.56
    पया
    -0.56
    POSITIVE LOGITS
    ValueGeneration
    0.51
    getFullYear
    0.49
    AddTagHelper
    0.49
    CppMethod
    0.47
     Confused
    0.47
     Reporter
    0.47
    AndEndTag
    0.47
    RRect
    0.46
    Revenir
    0.42
    :"-"`
    0.41
    Activations Density 0.045%

    No Known Activations