© 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. 0-CLT-HP
    7. 45220
    Prev
    Next
    INDEX
    Explanations

    programming instructions/debugging

    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
     Food
    -0.64
     Energy
    -0.61
     Residence
    -0.59
     Age
    -0.58
     Surface
    -0.58
     Life
    -0.58
     Sport
    -0.56
     Sleep
    -0.55
     Air
    -0.55
     Water
    -0.54
    POSITIVE LOGITS
     enfans
    0.67
     kautta
    0.65
     brancas
    0.65
     femininas
    0.64
     femininos
    0.62
     dieux
    0.61
     Monfieur
    0.61
     aikaa
    0.60
     myſelf
    0.58
     CMake
    0.58
    Activations Density 0.516%

    No Known Activations