© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1450
    Prev
    Next
    INDEX
    Explanations

    Over/Under

    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
     Over
    -0.93
    Over
    -0.93
     Under
    -0.79
    OVER
    -0.71
    Under
    -0.70
     OVER
    -0.60
     Through
    -0.52
    オーバー
    -0.50
     UNDER
    -0.49
    sci
    -0.48
    POSITIVE LOGITS
    ly
    1.12
    Personensuche
    1.04
    whelming
    1.04
    neath
    0.96
    tened
    0.89
     autorytatywna
    0.88
    Brainz
    0.87
    warded
    0.85
    theless
    0.84
    twimg
    0.83
    Activations Density 0.206%

    No Known Activations