© 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. 40104
    Prev
    Next
    INDEX
    Explanations

    names

    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
     Theſe
    -1.08
     Monfieur
    -1.08
     Diſ
    -1.07
     Reſ
    -1.03
     Beſ
    -1.00
     myſelf
    -1.00
     itſelf
    -0.99
     Perſ
    -0.99
     auffi
    -0.98
     Inſ
    -0.98
    POSITIVE LOGITS
     L
    0.64
     '\\;'
    0.61
     ostavi
    0.58
     kasarigan
    0.57
     J
    0.55
     jScrollPane
    0.55
     I
    0.54
     O
    0.52
     K
    0.52
     E
    0.52
    Activations Density 1.585%

    No Known Activations