© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9533
    Prev
    Next
    INDEX
    Explanations

    "#"

    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
     InputDecoration
    -0.59
    CloseOperation
    -0.59
    /*---
    -0.57
    msgTypes
    -0.56
    IsContent
    -0.51
    ház
    -0.50
    migrationBuilder
    -0.49
    kháu
    -0.49
    ="'.$
    -0.49
    TemporalType
    -0.48
    POSITIVE LOGITS
     noDo
    0.65
    Personensuche
    0.64
    ſelf
    0.59
     beſt
    0.58
     leaſt
    0.57
    دانشنامهٔ
    0.57
     whoſe
    0.56
     GDR
    0.54
     firſt
    0.54
     Jen
    0.52
    Activations Density 0.003%

    No Known Activations