© 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. 5-CLT-HP
    7. 92884
    Prev
    Next
    INDEX
    Explanations

    ne

    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
     his
    -0.59
     project
    -0.49
    期刊论文
    -0.48
     room
    -0.48
    nande
    -0.46
    ROGEN
    -0.45
    nya
    -0.45
     roots
    -0.44
    Czytaj
    -0.43
     kita
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.85
    awtextra
    0.69
    GraphicsUnit
    0.66
    sidemargin
    0.66
     فريبيس
    0.66
    AddHtmlAttribute
    0.63
     @"/
    0.61
    AccessorTable
    0.61
     ProtoMessage
    0.61
     MenuView
    0.59
    Activations Density 0.000%

    No Known Activations