© 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. 38673
    Prev
    Next
    INDEX
    Explanations

    Deficient/removed

    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
     AssemblyCulture
    -1.05
    MLLoader
    -1.02
    lower
    -1.01
     LOWER
    -0.95
    Lower
    -0.92
     lower
    -0.87
     Lower
    -0.85
     kasarigan
    -0.83
    lost
    -0.81
    InitVars
    -0.81
    POSITIVE LOGITS
     
    0.68
    diğinde
    0.51
     most
    0.51
     efficient
    0.50
     type
    0.48
     il
    0.47
    displaymath
    0.47
    トン
    0.46
     del
    0.46
     single
    0.46
    Activations Density 0.030%

    No Known Activations