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. 74383
    Prev
    Next
    INDEX
    Explanations

    Computer and network security

    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
    oredCriteria
    -0.79
     Paglinawan
    -0.68
     gyhoeddwyd
    -0.68
    Personendaten
    -0.67
    paksa
    -0.65
     AssemblyCulture
    -0.64
    gorm
    -0.63
    
    -0.63
    aarrggbb
    -0.62
    antaine
    -0.62
    POSITIVE LOGITS
     command
    0.54
     Command
    0.49
    holz
    0.46
    ('/:
    0.46
     infrastructure
    0.43
    il
    0.43
     C
    0.42
    jwa
    0.42
    AddRange
    0.41
    miz
    0.41
    Activations Density 0.002%

    No Known Activations