© 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. 90859
    Prev
    Next
    INDEX
    Explanations

    parts

    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
     part
    -0.91
     parts
    -0.91
     portions
    -0.77
     portion
    -0.73
     parte
    -0.71
    PARTS
    -0.66
     purpoſe
    -0.62
    parts
    -0.61
     bagian
    -0.61
    portion
    -0.61
    POSITIVE LOGITS
     فريبيس
    0.70
     createState
    0.65
    ConstraintMaker
    0.59
    tvguidetime
    0.58
    GEBURTSDATUM
    0.58
    CreateModel
    0.56
    rungsseite
    0.52
     arşivlendi
    0.51
    //
    0.50
    تقاوى
    0.50
    Activations Density 0.088%

    No Known Activations