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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74305
    Prev
    Next
    INDEX
    Explanations

    code 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
     pinulongan
    -0.82
     مشين
    -0.81
    AddTagHelper
    -0.77
    +#+
    -0.76
    Datuak
    -0.73
     المعيارى
    -0.73
     estimés
    -0.72
    RenderAtEndOf
    -0.71
     AspNetCore
    -0.70
     تانيه
    -0.69
    POSITIVE LOGITS
     -
    0.41
    Cor
    0.37
    iser
    0.37
    FRC
    0.37
    DT
    0.36
    FormState
    0.36
     Race
    0.35
     stood
    0.35
    TI
    0.35
    desta
    0.34
    Activations Density 0.011%

    No Known Activations