© 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. 1-CLT-HP
    7. 425
    Prev
    Next
    INDEX
    Explanations

    raw

    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
    raw
    -1.56
     raw
    -1.41
    Raw
    -1.22
     Raw
    -1.12
    RAW
    -0.95
     RAW
    -0.87
    hu
    -0.56
    BufferException
    -0.54
     uncut
    -0.53
    cius
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.75
    WebElementEntity
    0.69
    RSpec
    0.68
    tanleria
    0.63
    Diweddarwch
    0.63
    PerformLayout
    0.62
    }))
    0.62
     GenerationType
    0.60
    fromCharCode
    0.60
    WriteTagHelper
    0.57
    Activations Density 0.010%

    No Known Activations