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. 74397
    Prev
    Next
    INDEX
    Explanations

    Rwand

    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
     protoimpl
    -0.62
    +#+#
    -0.54
    OGND
    -0.47
    MIDDLEWARE
    -0.45
     contextLoads
    -0.45
    endwhile
    -0.43
    ftance
    -0.42
    ServletException
    -0.42
    StoryboardSegue
    -0.42
     חיצוניים
    -0.40
    POSITIVE LOGITS
    ://$
    0.57
     deserto
    0.57
     CreateTagHelper
    0.57
    [--
    0.57
    الحياه
    0.55
     TextAlign
    0.54
     affich
    0.54
     Wikispecies
    0.54
    sizeCache
    0.53
    AnimationsModule
    0.52
    Activations Density 0.000%

    No Known Activations