© 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. 40976
    Prev
    Next
    INDEX
    Explanations

    let

    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
     
    -0.68
    .
    -0.58
     (
    -0.57
    <eos>
    -0.50
     :
    -0.49
    ir
    -0.47
     ("
    -0.47
    '
    -0.47
    kunden
    -0.46
     .
    -0.45
    POSITIVE LOGITS
     Jefus
    0.98
     itſelf
    0.93
    Datuak
    0.88
     pleaſure
    0.86
    FunctionFlags
    0.83
     myſelf
    0.83
     himſelf
    0.83
     ―――――
    0.81
     تضيفلها
    0.80
    WithIOException
    0.77
    Activations Density 0.080%

    No Known Activations