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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 604
    Prev
    Next
    INDEX
    Explanations

    dys

    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
     تعدى
    -0.73
     itchy
    -0.71
     itching
    -0.66
     voices
    -0.65
    ifrance
    -0.64
     Formosa
    -0.63
    expandindo
    -0.61
     vertigo
    -0.61
     Arjuna
    -0.60
    脚注の使い方
    -0.59
    POSITIVE LOGITS
    ArgsConstructor
    0.57
    rha
    0.55
     <>",
    0.54
     Gra
    0.53
    دانشنامهٔ
    0.51
    Spoljašnje
    0.50
     ostavi
    0.50
    SharedDtor
    0.49
    клопе
    0.48
     useEffect
    0.47
    Activations Density 0.335%

    No Known Activations