© 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. 40567
    Prev
    Next
    INDEX
    Explanations

    shines

    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
     Efq
    -1.27
     Monfieur
    -1.12
     myſelf
    -1.10
     Jefus
    -1.06
     Theſe
    -1.02
     purpoſe
    -1.02
     Majefty
    -0.98
     ſeveral
    -0.98
     Reſ
    -0.98
     pleaſure
    -0.97
    POSITIVE LOGITS
     fa
    0.56
     of
    0.54
     av
    0.51
     
    0.49
     di
    0.48
     tap
    0.48
     zone
    0.48
     dot
    0.48
     Tab
    0.48
     lo
    0.47
    Activations Density 0.214%

    No Known Activations