© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6310
    Prev
    Next
    INDEX
    Explanations

    cheap technology

    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
    Negative Logits
     inexpensive
    -1.07
     cheap
    -1.04
     affordable
    -1.02
     Cheap
    -0.88
     cheapest
    -0.86
     cheaper
    -0.82
    Cheap
    -0.82
     cheaply
    -0.82
    affordable
    -0.81
     low
    -0.78
    POSITIVE LOGITS
     nahilalakip
    0.75
    ViewImports
    0.70
     ModelExpression
    0.68
     esternos
    0.68
    AndEndTag
    0.67
    thâu
    0.67
     protoimpl
    0.66
     trajets
    0.65
    ंदीखरीदारी
    0.64
    Diwedd
    0.64
    Activations Density 0.013%

    No Known Activations