© 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. 0-CLT-HP
    7. 92385
    Prev
    Next
    INDEX
    Explanations

    ada

    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
    ada
    -1.69
    ADA
    -0.96
     Ada
    -0.65
    adas
    -0.65
    adda
    -0.62
    adah
    -0.61
    Ada
    -0.59
    forName
    -0.57
    adam
    -0.53
    bow
    -0.51
    POSITIVE LOGITS
    EDEFAULT
    0.66
    UnusedPrivate
    0.65
    migrationBuilder
    0.65
     gainera
    0.64
    ďaka
    0.57
    endregion
    0.56
     @"/
    0.56
    
    0.56
     AssemblyVersion
    0.54
     TextEditing
    0.54
    Activations Density 0.048%

    No Known Activations