© 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. 4-CLT-HP
    7. 4745
    Prev
    Next
    INDEX
    Explanations

    informational/technical content

    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
     CreateTagHelper
    -0.68
    ScopeManager
    -0.65
    MethodManager
    -0.64
    تقاوى
    -0.54
    ksikon
    -0.53
     Roskov
    -0.53
    queryInterface
    -0.51
    Personendaten
    -0.48
     EClass
    -0.48
    schaft
    -0.48
    POSITIVE LOGITS
     pages
    0.57
     onPage
    0.57
    pagest
    0.57
    webgl
    0.56
     page
    0.56
     Page
    0.54
     PAGES
    0.53
     enca
    0.52
     Pages
    0.50
    ]=="
    0.50
    Activations Density 0.002%

    No Known Activations