© 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. 1501
    Prev
    Next
    INDEX
    Explanations

    containing the word "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
     kids
    -1.01
     flat
    -0.99
     parks
    -0.94
     flats
    -0.82
    flat
    -0.81
     flatter
    -0.77
     park
    -0.76
     FLAT
    -0.75
    waitKey
    -0.73
    kids
    -0.70
    POSITIVE LOGITS
     described
    0.50
    SequentialGroup
    0.49
     of
    0.48
    iornamento
    0.47
     recently
    0.43
     identified
    0.43
     received
    0.42
     released
    0.42
     and
    0.41
     trăm
    0.41
    Activations Density 0.080%

    No Known Activations