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. 73890
    Prev
    Next
    INDEX
    Explanations

    code and research snippets

    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
    料
    -0.53
    iscus
    -0.50
     light
    -0.50
    table
    -0.49
     table
    -0.48
    esc
    -0.47
    umman
    -0.47
     flag
    -0.47
    isabeth
    -0.47
     {"
    -0.47
    POSITIVE LOGITS
    gridx
    0.73
     doInBackground
    0.70
     NSCoder
    0.60
    ]")]
    0.59
    MessageTagHelper
    0.59
    brainly
    0.57
    NewUrlParser
    0.57
     onCreateView
    0.56
    ReusableCell
    0.56
     ویکی‌پدیا
    0.55
    Activations Density 0.002%

    No Known Activations