© 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. 1-CLT-HP
    7. 725
    Prev
    Next
    INDEX
    Explanations

    on

    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
     wijze
    -0.59
     démocr
    -0.57
     fédé
    -0.54
    emény
    -0.52
    guruan
    -0.52
    /$
    -0.51
    ését
    -0.50
     tenté
    -0.50
    kháu
    -0.49
    ftet
    -0.49
    POSITIVE LOGITS
     promoting
    0.77
     reducing
    0.74
     addressing
    0.73
     boosting
    0.69
     preserving
    0.69
     ending
    0.69
     supporting
    0.67
     enhancing
    0.66
     protecting
    0.66
     regulating
    0.66
    Activations Density 0.014%

    No Known Activations