© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1667
    Prev
    Next
    INDEX
    Explanations

    degree

    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
    thalam
    -0.50
    illette
    -0.48
     lendemain
    -0.46
     gereken
    -0.45
     halfway
    -0.45
    忽然
    -0.45
     sube
    -0.45
    лтемелер
    -0.43
    ESIS
    -0.43
    κλη
    -0.43
    POSITIVE LOGITS
    providedIn
    0.80
     this
    0.75
    findpost
    0.75
    Datuak
    0.74
    MigrationBuilder
    0.73
    下载附件
    0.66
    InputTagHelper
    0.66
    AndEndTag
    0.65
    sizeCache
    0.63
     or
    0.62
    Activations Density 0.001%

    No Known Activations