© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8966
    Prev
    Next
    INDEX
    Explanations

    ancient civilizations

    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
     ancient
    -0.62
     antica
    -0.54
     antiche
    -0.51
     ancienne
    -0.49
    ancient
    -0.48
    Ancient
    -0.48
     záz
    -0.45
     Ancient
    -0.45
     tomber
    -0.44
     древ
    -0.44
    POSITIVE LOGITS
    WithIOException
    0.88
    kháu
    0.84
    OrBuilder
    0.83
     ProtoMessage
    0.81
    >{@
    0.81
    titleMargin
    0.78
     propOrder
    0.77
    RegressionTest
    0.77
     становника
    0.77
    SBATCH
    0.76
    Activations Density 0.009%

    No Known Activations