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. 20-CLT-HP
    4. 73815
    Prev
    Next
    INDEX
    Explanations

    .

    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
     ſever
    -0.61
     pleaſure
    -0.60
     purpoſe
    -0.60
     ſtate
    -0.55
     Reſ
    -0.54
     ſta
    -0.54
     ſeveral
    -0.54
     Diſ
    -0.52
     Houſe
    -0.52
     ſche
    -0.52
    POSITIVE LOGITS
     referenties
    0.80
     To
    0.78
     On
    0.77
     At
    0.76
     سكانية
    0.73
     By
    0.72
     Over
    0.72
     go
    0.72
    expandindo
    0.71
     Chwiliwch
    0.70
    Activations Density 0.001%

    No Known Activations