© 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. 43517
    Prev
    Next
    INDEX
    Explanations

    macro

    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
     macro
    -1.16
    Macro
    -1.05
     Macro
    -1.03
    macro
    -0.97
     MACRO
    -0.93
     macros
    -0.83
     macroeconomic
    -0.82
    Primary
    -0.77
     macron
    -0.74
     makro
    -0.71
    POSITIVE LOGITS
    出版年
    0.69
     Stop
    0.55
     nahilalakip
    0.54
     stop
    0.53
     escala
    0.52
     Scale
    0.51
     fumée
    0.51
    RTEE
    0.51
     Care
    0.48
    AZINE
    0.47
    Activations Density 0.120%

    No Known Activations