Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45130
    Prev
    Next
    INDEX
    Explanations

    exponential

    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
     exponential
    -1.68
     Exponential
    -1.47
    Exponential
    -1.30
    exponential
    -1.19
     exponentially
    -1.13
     expon
    -0.96
     logarithmic
    -0.79
     indisponible
    -0.66
     logarith
    -0.62
     Daß
    -0.62
    POSITIVE LOGITS
     ostavi
    0.61
     /\.
    0.60
    ScopeManager
    0.60
     calldata
    0.52
     ba
    0.51
    cplusplus
    0.50
    ╗
    0.48
    Contd
    0.47
    gorm
    0.46
    TagMode
    0.46
    Activations Density 0.011%

    No Known Activations