© 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. 1852
    Prev
    Next
    INDEX
    Explanations

    radiology

    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
     a
    -0.71
     I
    -0.70
    r
    -0.69
     
    -0.69
    n
    -0.69
     the
    -0.63
     i
    -0.63
    ↵↵
    -0.62
    l
    -0.62
    x
    -0.62
    POSITIVE LOGITS
     Efq
    1.69
     Jefus
    1.61
     myſelf
    1.59
     ―――――
    1.55
     CreateTagHelper
    1.53
     ་་
    1.53
     itſelf
    1.52
     Monfieur
    1.50
     Majefty
    1.48
     doubtnut
    1.47
    Activations Density 0.046%

    No Known Activations