© 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. 92434
    Prev
    Next
    INDEX
    Explanations

    <

    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
    <
    -1.45
     <
    -1.41
     diameter
    -0.82
     District
    -0.77
    -<
    -0.69
    diameter
    -0.66
     
    -0.66
     than
    -0.65
    <(
    -0.65
     in
    -0.64
    POSITIVE LOGITS
     itſelf
    1.04
    ſelf
    0.96
    ſelves
    0.95
     myſelf
    0.93
     Majefty
    0.92
    tagHelperRunner
    0.90
     themſelves
    0.90
    parsedMessage
    0.89
     ―――――
    0.89
     Jefus
    0.87
    Activations Density 1.371%

    No Known Activations