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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4671
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    IUrlHelper
    -0.71
     destinées
    -0.69
     étend
    -0.66
     lørdag
    -0.66
     genoux
    -0.66
     chré
    -0.66
    RenderAtEndOf
    -0.65
     étrangères
    -0.63
     âgées
    -0.63
     coû
    -0.62
    POSITIVE LOGITS
    -
    0.95
     years
    0.66
     miles
    0.61
     percent
    0.56
     per
    0.53
    存于互联网档案馆
    0.53
     feet
    0.47
     ModelExpression
    0.46
     metres
    0.46
     eyes
    0.46
    Activations Density 0.002%

    No Known Activations