© 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. 5-CLT-HP
    7. 92799
    Prev
    Next
    INDEX
    Explanations

    Years

    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
     ModelExpression
    -0.81
    Datuak
    -0.76
     BoxDecoration
    -0.74
    Hentet
    -0.73
     kasarigan
    -0.73
    ContentAsync
    -0.68
    DotNetBar
    -0.68
    AnimationsModule
    -0.68
     onOptions
    -0.68
     snippetHide
    -0.68
    POSITIVE LOGITS
     ngành
    0.37
     handelt
    0.37
    -------------</
    0.36
    adə
    0.35
    '])){
    0.35
    sud
    0.35
    ništ
    0.33
    CROSSTALK
    0.31
    cdk
    0.31
    ↵↵↵
    0.31
    Activations Density 0.001%

    No Known Activations