Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74207
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     propOrder
    -0.78
    
    -0.75
     CreateTagHelper
    -0.72
     endregion
    -0.71
     Collapse
    -0.66
    tonsoft
    -0.66
    +#+#
    -0.65
    anneer
    -0.65
     pleaſure
    -0.65
     useSelector
    -0.64
    POSITIVE LOGITS
    Hep
    0.48
     /*#__
    0.46
    ftagPool
    0.45
     Hep
    0.42
    المشاركات
    0.42
    liferay
    0.42
    OpenHelper
    0.40
     Immun
    0.40
     pre
    0.40
    Immun
    0.38
    Activations Density 0.001%

    No Known Activations