© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97367
    Prev
    Next
    INDEX
    Explanations

    Technology and electronic devices

    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
     (
    -0.48
     competitors
    -0.31
     complaints
    -0.31
    ResponseWriter
    -0.30
     specification
    -0.30
    きの
    -0.29
     turning
    -0.28
    向けの
    -0.28
     marches
    -0.28
     compagnon
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.93
    новништво
    0.91
     AssemblyCulture
    0.85
    TagMode
    0.83
    windowFixed
    0.82
     indisponible
    0.81
    +#+#
    0.80
    AndroidJUnit
    0.79
    Tikang
    0.77
     Biôgrafia
    0.77
    Activations Density 0.514%

    No Known Activations