© 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. 4-CLT-HP
    7. 3435
    Prev
    Next
    INDEX
    Explanations

    the

    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
    CompleteListener
    -0.65
    bootstrapcdn
    -0.58
    nestjs
    -0.52
    :✨
    -0.50
    FetchType
    -0.48
     linh
    -0.47
    tanleria
    -0.47
    djangoproject
    -0.46
    internalType
    -0.46
     simila
    -0.46
    POSITIVE LOGITS
    etheless
    0.58
     CreateTagHelper
    0.56
     _)
    0.54
    .”)
    0.53
    зулта
    0.52
     '\\;'
    0.51
    ècie
    0.51
    .”.
    0.50
    WEBPACK
    0.50
     وتسجيلات
    0.49
    Activations Density 0.018%

    No Known Activations