© 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. 3070
    Prev
    Next
    INDEX
    Explanations

    caused

    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
     EconPapers
    -0.86
    хьтан
    -0.64
    WithIOException
    -0.63
    chables
    -0.62
     الحره
    -0.62
     otomatig
    -0.60
    webElementXpaths
    -0.60
    uxxxx
    -0.60
    migrationBuilder
    -0.57
     GenerationType
    -0.57
    POSITIVE LOGITS
     by
    0.63
     because
    0.63
     when
    0.59
    rouvez
    0.57
     due
    0.50
     indirectly
    0.50
     porque
    0.49
     whereby
    0.47
     becau
    0.47
     bởi
    0.46
    Activations Density 0.002%

    No Known Activations