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. 1-CLT-HP
    4. 12906
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    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
    oria
    -1.96
    ORIA
    -1.63
    aya
    -1.30
    orias
    -1.18
    AYA
    -1.05
    oriya
    -0.70
    ayah
    -0.63
    ória
    -0.57
    ayas
    -0.56
    ayaan
    -0.56
    POSITIVE LOGITS
    RegistryLite
    0.71
     nakalista
    0.69
    PerformLayout
    0.69
    AnchorStyles
    0.68
    LEncoder
    0.65
     verwijzen
    0.63
    BeginInit
    0.63
    
    0.62
     noDo
    0.62
    principalColumn
    0.61
    Activations Density 0.067%

    No Known Activations