© 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. 91200
    Prev
    Next
    INDEX
    Explanations

    words

    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
    sizeCache
    -0.73
    contentLoaded
    -0.71
    SpringRunner
    -0.71
    permum
    -0.63
    webElementXpaths
    -0.62
    TintMode
    -0.62
     ujednoznacz
    -0.61
    OutputType
    -0.61
    AutoField
    -0.60
     Италијани
    -0.60
    POSITIVE LOGITS
     of
    1.00
    s
    0.48
     enough
    0.47
     everything
    0.45
     there
    0.43
     Então
    0.43
     ognuno
    0.42
     then
    0.42
     really
    0.42
    enough
    0.41
    Activations Density 0.273%

    No Known Activations