© 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. 90442
    Prev
    Next
    INDEX
    Explanations

    flat

    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
     flat
    -1.44
     Flat
    -1.35
    Flat
    -1.33
    flat
    -1.29
     FLAT
    -1.24
    FLAT
    -0.91
    hot
    -0.84
     flatter
    -0.75
    フラット
    -0.70
     hot
    -0.69
    POSITIVE LOGITS
    🏻
    0.70
    tened
    0.69
    tings
    0.68
    ters
    0.66
    tors
    0.65
    tled
    0.64
    sterious
    0.64
     becauſe
    0.63
    ting
    0.62
    tening
    0.61
    Activations Density 0.048%

    No Known Activations