© 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. 90514
    Prev
    Next
    INDEX
    Explanations

    guan

    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
    -1.95
     myſelf
    -1.95
     Monfieur
    -1.77
     pleaſure
    -1.76
     Houſe
    -1.70
     Jefus
    -1.66
     Majefty
    -1.65
     houſe
    -1.63
     purpoſe
    -1.63
     themſelves
    -1.62
    POSITIVE LOGITS
     der
    0.73
     d
    0.68
     u
    0.65
     di
    0.64
     t
    0.63
     or
    0.63
     er
    0.62
     par
    0.62
     su
    0.61
     '
    0.61
    Activations Density 0.362%

    No Known Activations