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. 45242
    Prev
    Next
    INDEX
    Explanations

    charter

    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
     chartered
    -1.43
     Chartered
    -1.17
     charter
    -1.00
    charter
    -0.93
     CreateTagHelper
    -0.85
    rungsseite
    -0.79
    Попис
    -0.79
     charters
    -0.77
    himovic
    -0.77
    цездатний
    -0.75
    POSITIVE LOGITS
    Datuak
    0.53
    σθαι
    0.45
     Stage
    0.45
    Diweddarwch
    0.43
     presentarse
    0.43
    Stage
    0.43
    ysis
    0.43
    期
    0.42
    mű
    0.42
     stage
    0.42
    Activations Density 0.036%

    No Known Activations