© 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. 1879
    Prev
    Next
    INDEX
    Explanations

    Windows operating system

    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
    ore
    -0.87
    fore
    -0.71
     fore
    -0.71
     Windows
    -0.66
    Windows
    -0.65
    side
    -0.60
    ers
    -0.55
    less
    -0.55
    hams
    -0.53
    ORE
    -0.53
    POSITIVE LOGITS
    TagMode
    0.80
    ContentAsync
    0.75
    HomeAsUpEnabled
    0.73
    ollary
    0.73
     helst
    0.71
    becken
    0.71
     hâte
    0.70
     vė
    0.69
    ratulations
    0.69
     bocca
    0.68
    Activations Density 0.409%

    No Known Activations