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. 74596
    Prev
    Next
    INDEX
    Explanations

    incidents

    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
     Disaster
    -1.34
    Disaster
    -1.32
    Accident
    -1.13
     Accident
    -1.10
    disaster
    -1.05
    accident
    -1.05
     accident
    -1.05
     ACCIDENT
    -1.03
     Crisis
    -1.00
     catastrophe
    -0.98
    POSITIVE LOGITS
    indo
    0.39
    脚注の使い方
    0.35
    offrir
    0.35
    Ler
    0.33
    ъ
    0.33
    LikeLike
    0.33
    ardo
    0.32
    abel
    0.32
    Wrap
    0.32
    oban
    0.31
    Activations Density 0.046%

    No Known Activations