© 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. 5-CLT-HP
    7. 94735
    Prev
    Next
    INDEX
    Explanations

    time of year

    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
     CURIAM
    -0.69
    TypedDataSet
    -0.67
    MigrationBuilder
    -0.65
    sizeCache
    -0.64
    jooq
    -0.58
    COUVER
    -0.58
     års
    -0.56
    ophon
    -0.52
    قایناقلار
    -0.52
     seasonally
    -0.51
    POSITIVE LOGITS
     thereafter
    0.74
    InSection
    0.68
     afterwards
    0.65
     eventual
    0.64
     subsequently
    0.63
    TagHelper
    0.63
     subsequent
    0.62
     Thereafter
    0.61
     eventually
    0.60
     Subsequent
    0.58
    Activations Density 0.083%

    No Known Activations