Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74563
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    ConstraintMaker
    -0.96
    argout
    -0.85
     Normdatei
    -0.83
    makeConstraints
    -0.82
     ExecuteAsync
    -0.81
    +#+#
    -0.81
    IUrlHelper
    -0.81
    __":
    
    -0.80
    клопе
    -0.79
     CWE
    -0.79
    POSITIVE LOGITS
     st
    0.42
     bestehenden
    0.39
     godk
    0.36
     numéros
    0.35
     Ste
    0.35
     la
    0.34
     computadoras
    0.34
     La
    0.34
     sillas
    0.33
     arbet
    0.33
    Activations Density 0.040%

    No Known Activations