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. 74524
    Prev
    Next
    INDEX
    Explanations

    folder

    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
    </caption>
    -0.82
    Gambas
    -0.80
     Савезне
    -0.67
    tvguidetime
    -0.65
    ftagPool
    -0.64
     AssemblyCompany
    -0.63
     }}"></
    -0.62
     vPvB
    -0.61
     isInitialized
    -0.61
    ItemBackground
    -0.61
    POSITIVE LOGITS
     ProtoMessage
    0.48
    ิ่ง
    0.42
     Tank
    0.41
     tank
    0.40
     march
    0.39
    ün
    0.38
     électroniques
    0.38
     tanques
    0.38
     calculées
    0.38
     March
    0.37
    Activations Density 0.010%

    No Known Activations