© 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. 20-CLT-HP
    7. 71722
    Prev
    Next
    INDEX
    Explanations

    Federal

    np_max-act-logits · 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
    expandindo
    -0.78
     تضيفلها
    -0.78
    SourceChecksum
    -0.70
     ExecuteAsync
    -0.69
     internetowa
    -0.68
    Autoritní
    -0.65
     <<<<<<<<<<<<<<
    -0.64
     незавершена
    -0.63
     nakalista
    -0.63
     transférez
    -0.60
    POSITIVE LOGITS
     Trade
    0.74
     trade
    0.65
     TRADE
    0.63
     Communications
    0.59
    trade
    0.59
    Trade
    0.58
    ProgressHUD
    0.50
     COMMUNICATIONS
    0.48
     Sent
    0.48
     елның
    0.48
    Activations Density 0.001%

    No Known Activations