© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42662
    Prev
    Next
    INDEX
    Explanations

    emphasize

    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
     emphasis
    -2.36
     emphasize
    -2.33
     emphasise
    -2.25
     Emphasis
    -2.20
    emphasis
    -2.08
     emphasizing
    -2.06
     emphasizes
    -2.03
     emphasized
    -2.02
     emphas
    -1.99
     Emphas
    -1.91
    POSITIVE LOGITS
     on
    0.89
    ally
    0.57
     On
    0.57
    ise
    0.55
    ize
    0.54
     that
    0.52
    ,
    0.52
    .
    0.51
     best
    0.50
     upon
    0.50
    Activations Density 0.041%

    No Known Activations