© 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. 1-CLT-HP
    7. 46319
    Prev
    Next
    INDEX
    Explanations

    unusual text

    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
     propOrder
    -0.71
    bootstrapcdn
    -0.66
    AccessorTable
    -0.65
    IndentedString
    -0.62
    ChildScrollView
    -0.59
    InjectAttribute
    -0.58
     AssemblyCulture
    -0.57
    adaptiveStyles
    -0.57
     autorytatywna
    -0.57
     /\.
    -0.56
    POSITIVE LOGITS
    yelidikan
    0.59
     AllAfrica
    0.53
     mulia
    0.49
    agog
    0.47
    unteers
    0.45
    Individuals
    0.44
    orious
    0.44
    zunehmen
    0.44
     near
    0.43
    urous
    0.43
    Activations Density 0.073%

    No Known Activations