© 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. 45402
    Prev
    Next
    INDEX
    Explanations

    Pak

    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
     Lyndon
    -1.19
     pleaſure
    -1.02
     itſelf
    -1.00
     myſelf
    -1.00
     تضيفلها
    -0.99
     auffi
    -0.98
     purpoſe
    -0.97
    AndEndTag
    -0.95
    SourceChecksum
    -0.94
    httphttps
    -0.94
    POSITIVE LOGITS
     A
    0.56
     
    0.56
     n
    0.51
     B
    0.50
     (
    0.48
     de
    0.47
     L
    0.47
     e
    0.46
     N
    0.46
    ,
    0.46
    Activations Density 1.157%

    No Known Activations