© 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. 4817
    Prev
    Next
    INDEX
    Explanations

    by

    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
     asses
    -0.41
     wider
    -0.40
     broader
    -0.40
    ợi
    -0.40
     wide
    -0.39
     slit
    -0.38
     guts
    -0.38
     broad
    -0.37
    什么是
    -0.36
    Seg
    -0.36
    POSITIVE LOGITS
    GEBURTSDATUM
    0.93
    expandindo
    0.85
     समीक्षक
    0.82
     متعلقه
    0.81
    rungsseite
    0.80
    Portale
    0.77
    astify
    0.77
    EndGlobalSection
    0.77
     AssemblyCompany
    0.77
    webElementXpaths
    0.73
    Activations Density 0.015%

    No Known Activations