© 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. 97433
    Prev
    Next
    INDEX
    Explanations

    sorting, exporting, importing

    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
     exporting
    -1.11
     importing
    -1.07
     Imports
    -1.06
     exports
    -1.02
     exported
    -1.01
     importers
    -1.01
     imports
    -1.00
     Importing
    -0.97
     exporter
    -0.96
     export
    -0.96
    POSITIVE LOGITS
    s
    1.02
    ers
    0.60
     correctes
    0.54
    ervlak
    0.51
    iastes
    0.49
     EconPapers
    0.45
    n
    0.45
    ings
    0.44
    casian
    0.44
    ism
    0.43
    Activations Density 0.126%

    No Known Activations