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. 74244
    Prev
    Next
    INDEX
    Explanations

    mixed languages and 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
     <=",
    -0.58
     pamamagitan
    -0.51
    ]:
    
    -0.49
    usermodel
    -0.49
    νει
    -0.48
    cyjny
    -0.48
     NSError
    -0.46
    #+#
    -0.46
     stratégique
    -0.46
     createState
    -0.45
    POSITIVE LOGITS
     الحره
    0.65
    StoryboardSegue
    0.61
     ویکی‌پدیا
    0.57
     chi̍t
    0.51
     blind
    0.49
    IsContent
    0.48
    AccessorTable
    0.47
    archiviato
    0.47
    RenderAtEndOf
    0.46
     vuitton
    0.46
    Activations Density 0.016%

    No Known Activations