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. 20-CLT-HP
    4. 74136
    Prev
    Next
    INDEX
    Explanations

    universities

    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
     تكبرها
    -0.66
     dataTable
    -0.64
     DOCTOR
    -0.62
    脚注の使い方
    -0.61
     HasFactory
    -0.61
     légales
    -0.60
    ंदीखरीदारी
    -0.60
     '{@
    -0.59
     doctor
    -0.59
     createSprite
    -0.59
    POSITIVE LOGITS
     School
    0.47
    ธิ
    0.41
     WaitForSeconds
    0.39
     qua
    0.38
     Per
    0.37
     exhaus
    0.37
     szerző
    0.37
     reproducción
    0.36
    StoryboardSegue
    0.36
     هيا
    0.35
    Activations Density 0.002%

    No Known Activations