© 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. 97298
    Prev
    Next
    INDEX
    Explanations

    examination

    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
     examination
    -0.99
    examination
    -0.88
     Examination
    -0.85
    Examination
    -0.77
    ist
    -0.63
     mi
    -0.62
     EXAMINATION
    -0.62
    mi
    -0.60
     examinations
    -0.59
    mos
    -0.57
    POSITIVE LOGITS
     pleaſure
    0.75
    ſelf
    0.74
     itſelf
    0.73
    MarshalTo
    0.73
     whereof
    0.72
     myſelf
    0.71
     stiefel
    0.70
     Jefus
    0.69
     Où
    0.67
     salomon
    0.66
    Activations Density 0.087%

    No Known Activations