© 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. 92597
    Prev
    Next
    INDEX
    Explanations

    Uncommon words/names/code

    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
     fram
    -0.49
    ness
    -0.49
    rl
    -0.47
     vie
    -0.47
    bye
    -0.46
    fts
    -0.45
     sch
    -0.44
    います
    -0.44
    .
    -0.42
     via
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    0.86
    InSection
    0.76
    WithIOException
    0.75
    MessageTagHelper
    0.74
     newBuilder
    0.73
     Cæsar
    0.71
     Италијани
    0.69
     препратки
    0.68
     minOccurs
    0.67
     NSCoder
    0.67
    Activations Density 0.161%

    No Known Activations