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. 74516
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    Bangladesh
    -0.45
    Maui
    -0.43
    listFiles
    -0.43
    Elliott
    -0.42
    Senegal
    -0.41
     Bangladesh
    -0.40
    Thai
    -0.40
    Sri
    -0.40
    peru
    -0.39
    Tog
    -0.39
    POSITIVE LOGITS
    ſelf
    0.83
     Jefus
    0.81
     Houſe
    0.81
     myſelf
    0.80
     Diſ
    0.79
     ſever
    0.79
     iſt
    0.79
     Efq
    0.79
     fevere
    0.77
     Majefty
    0.77
    Activations Density 0.078%

    No Known Activations