© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97120
    Prev
    Next
    INDEX
    Explanations

    economics

    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
     Recession
    -0.79
     recession
    -0.74
     Array
    -0.73
     array
    -0.72
     ArrayAdapter
    -0.64
    jooq
    -0.60
    Geografi
    -0.59
    '])){
    
    -0.58
     ARRAY
    -0.57
    cydow
    -0.57
    POSITIVE LOGITS
    ing
    0.84
    ed
    0.79
    ers
    0.71
    ally
    0.71
    ian
    0.71
    als
    0.69
    ary
    0.68
    ation
    0.64
    ist
    0.61
    aries
    0.56
    Activations Density 0.329%

    No Known Activations