© 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. 92637
    Prev
    Next
    INDEX
    Explanations

    extended

    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
    setVerticalGroup
    -0.80
    aarrggbb
    -0.71
    ArrowToggle
    -0.71
    ScopeManager
    -0.69
    igshid
    -0.69
     CreateTagHelper
    -0.66
    Cordialement
    -0.64
    visející
    -0.62
    IUrlHelper
    -0.62
    MigrationBuilder
    -0.61
    POSITIVE LOGITS
    0.51
    0.50
     numerator
    0.49
    0.48
    ful
    0.48
    InjectMocks
    0.47
    uchs
    0.47
    GIVEREF
    0.47
     isothermal
    0.47
    HEET
    0.46
    Activations Density 0.157%

    No Known Activations