© 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. 97223
    Prev
    Next
    INDEX
    Explanations

    conflicts

    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
     itſelf
    -1.54
     myſelf
    -1.49
     Majefty
    -1.41
     ſeveral
    -1.41
     Jefus
    -1.34
     Monfieur
    -1.31
     pleaſure
    -1.29
     ſtate
    -1.26
     Efq
    -1.26
     purpoſe
    -1.24
    POSITIVE LOGITS
     to
    0.69
     or
    0.69
     (
    0.66
     
    0.62
    /
    0.59
     and
    0.58
     $
    0.55
     ch
    0.54
     one
    0.54
    ↵↵
    0.54
    Activations Density 1.488%

    No Known Activations