© 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. 355
    Prev
    Next
    INDEX
    Explanations

    Uncertainty/Possibility

    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
    AndEndTag
    -0.77
     EconPapers
    -0.70
     gärna
    -0.67
     perhaps
    -0.65
    perhaps
    -0.65
     تضيفلها
    -0.63
     misschien
    -0.63
     مرئيه
    -0.62
     arguably
    -0.61
    Maybe
    -0.60
    POSITIVE LOGITS
     esimer
    0.50
    HttpDelete
    0.48
    teborg
    0.47
    prelude
    0.46
    SpringBootTest
    0.46
    MenuInflater
    0.46
     indicative
    0.45
     jury
    0.45
    CATALOG
    0.45
    SEMICOLON
    0.44
    Activations Density 0.032%

    No Known Activations