© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43418
    Prev
    Next
    INDEX
    Explanations

    media

    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
     consecration
    -0.52
     cellar
    -0.52
     lyre
    -0.52
     ovary
    -0.51
    info
    -0.50
     Савезне
    -0.50
     lordship
    -0.50
     poetical
    -0.49
     inscriptions
    -0.49
     iguana
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.79
    脚注の使い方
    0.76
    mybatisplus
    0.73
     متعلقه
    0.69
    CompleteListener
    0.65
     CreateTagHelper
    0.64
    исленность
    0.62
    erton
    0.61
    PerformLayout
    0.60
    >),
    0.60
    Activations Density 0.097%

    No Known Activations