© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    Describing somebody's past

    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
    became
    -0.96
     Became
    -0.87
     became
    -0.86
     grew
    -0.84
     devint
    -0.81
     ferons
    -0.79
    began
    -0.79
     للمعارف
    -0.78
     mourut
    -0.76
    grew
    -0.74
    POSITIVE LOGITS
     a
    1.00
     an
    0.88
     the
    0.87
    <bos>
    0.80
    ↵↵
    0.77
     one
    0.73
     
    0.72
    ↵
    0.70
     so
    0.67
     some
    0.64
    Activations Density 0.034%

    No Known Activations