© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3522
    Prev
    Next
    INDEX
    Explanations

    vision, eyes, science

    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
    NOPQRST
    -0.72
     BoxDecoration
    -0.60
     مرئيه
    -0.57
    eachtet
    -0.57
    olidation
    -0.51
     InputDecoration
    -0.50
     Loma
    -0.50
     Legg
    -0.49
     endwhile
    -0.48
     Customization
    -0.47
    POSITIVE LOGITS
    __":
    0.58
     bio
    0.54
     oprot
    0.54
    ثمار
    0.49
    .*")]
    0.49
    __':
    0.47
     NavController
    0.46
    HomeAsUp
    0.46
    CppMethod
    0.44
     adb
    0.44
    Activations Density 0.002%

    No Known Activations