© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1983
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · 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
    consulté
    -0.69
    AndEndTag
    -0.63
    RenderAtEndOf
    -0.62
    antaranya
    -0.61
    StoryboardSegue
    -0.58
     ExecuteAsync
    -0.57
    TagMode
    -0.57
     pinulongan
    -0.55
    PhysRev
    -0.55
    archiviato
    -0.54
    POSITIVE LOGITS
     media
    0.84
     public
    0.63
     press
    0.62
    médi
    0.61
    MEDIA
    0.60
     Media
    0.58
     news
    0.56
    queryInterface
    0.56
    media
    0.54
     Grimal
    0.54
    Activations Density 0.014%

    No Known Activations