© 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. 97199
    Prev
    Next
    INDEX
    Explanations

    computers and programming

    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
     A
    -0.54
     
    -0.52
     $
    -0.50
     N
    -0.49
     pescoço
    -0.47
     T
    -0.46
    Aiheesta
    -0.43
     D
    -0.42
     Y
    -0.42
     The
    -0.42
    POSITIVE LOGITS
     Reſ
    0.88
     pleaſure
    0.86
    ſelf
    0.85
     NSCoder
    0.85
    ControllerAdvice
    0.84
     myſelf
    0.84
     ſtate
    0.83
     houſe
    0.82
     Majefty
    0.82
     itſelf
    0.81
    Activations Density 0.216%

    No Known Activations