© 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. 0-CLT-HP
    4. 38272
    Prev
    Next
    INDEX
    Explanations

    interviews

    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
     Efq
    -1.05
     roots
    -1.02
    RectangleBorder
    -0.97
     interviews
    -0.94
     traces
    -0.93
    rooted
    -0.93
     rooted
    -0.92
     itſelf
    -0.87
     rooting
    -0.86
     iſt
    -0.85
    POSITIVE LOGITS
     of
    0.59
     instead
    0.57
    y
    0.55
    a
    0.54
    o
    0.54
     crois
    0.53
    e
    0.52
     for
    0.51
     in
    0.50
    .
    0.49
    Activations Density 0.076%

    No Known Activations