© 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. 1-CLT-HP
    4. 11919
    Prev
    Next
    INDEX
    Explanations

    Harmon

    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
     harmon
    -1.06
    harmon
    -1.05
     harmonize
    -1.00
     armon
    -0.91
     harmony
    -0.85
    Harmon
    -0.82
    harmony
    -0.82
     harmonie
    -0.78
     Harmon
    -0.73
     harmonious
    -0.70
    POSITIVE LOGITS
     precincts
    0.63
    inquirer
    0.54
     MessageBoxIcon
    0.51
    ProgressHUD
    0.49
     mixes
    0.48
     BoxFit
    0.48
    AllowUser
    0.48
     Lightboxes
    0.48
    AutoField
    0.47
    uxxxx
    0.47
    Activations Density 0.006%

    No Known Activations