© 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. 94298
    Prev
    Next
    INDEX
    Explanations

    as

    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
     الحره
    -1.20
    expandindo
    -1.17
     jScrollPane
    -1.07
    UnsafeEnabled
    -1.01
    AndEndTag
    -1.00
    RegressionTest
    -0.98
     EconPapers
    -0.98
    parsedMessage
    -0.96
    Datuak
    -0.96
     Paglinawan
    -0.95
    POSITIVE LOGITS
     over
    0.51
     four
    0.49
     three
    0.42
    over
    0.42
     six
    0.41
     anywhere
    0.40
    t
    0.39
     as
    0.39
     between
    0.38
     five
    0.38
    Activations Density 0.002%

    No Known Activations