© 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. 41073
    Prev
    Next
    INDEX
    Explanations

    both

    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
     set
    -1.20
    Set
    -1.11
    set
    -1.07
     between
    -1.05
    Both
    -1.02
     setting
    -1.01
     Both
    -0.99
     Set
    -0.97
    both
    -0.96
    between
    -0.91
    POSITIVE LOGITS
     nahilalakip
    1.01
     purpoſe
    1.00
     pleaſure
    0.99
     myſelf
    0.97
     lenker
    0.94
    ſelf
    0.94
    出版年
    0.93
     Efq
    0.93
     ſmall
    0.93
     cherchés
    0.93
    Activations Density 0.164%

    No Known Activations