© 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. 20-CLT-HP
    7. 74612
    Prev
    Next
    INDEX
    Explanations

    back

    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
     to
    -0.76
    المشاركات
    -0.54
     للاسماء
    -0.52
     tol
    -0.49
    ]--;
    -0.48
     resourceCulture
    -0.48
    RTLE
    -0.47
    AllowUser
    -0.47
     جغرافيا
    -0.47
     betweenstory
    -0.47
    POSITIVE LOGITS
     at
    1.05
     in
    0.81
     tại
    0.71
     ở
    0.66
     rosse
    0.61
     At
    0.59
    At
    0.57
     propOrder
    0.55
     في
    0.53
    日在
    0.53
    Activations Density 0.001%

    No Known Activations