© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97563
    Prev
    Next
    INDEX
    Explanations

    AI

    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
     AI
    -1.79
    AI
    -1.60
     Artificial
    -0.88
     God
    -0.82
    Ai
    -0.81
     ai
    -0.79
     Ai
    -0.71
    CI
    -0.69
    Artificial
    -0.69
     artificial
    -0.67
    POSITIVE LOGITS
     estekak
    0.69
     contextLoads
    0.68
    脚注の使い方
    0.67
     mergeFrom
    0.66
    DispatchToProps
    0.57
     BoxDecoration
    0.56
    RunAsync
    0.56
     चीज़ों
    0.54
     يتيمه
    0.54
     Stare
    0.53
    Activations Density 0.032%

    No Known Activations