© 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. 5-CLT-HP
    7. 588
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
     Мексичка
    -1.04
     CreateTagHelper
    -0.96
    IntoConstraints
    -0.92
    RenderAtEndOf
    -0.91
    下载附件
    -0.90
    transQ
    -0.88
    UnusedPrivate
    -0.88
    ."));
    -0.87
    Personendaten
    -0.86
    Personensuche
    -0.86
    POSITIVE LOGITS
    <eos>
    0.50
     has
    0.46
     was
    0.43
     tells
    0.43
     does
    0.41
     is
    0.40
     says
    0.40
     can
    0.39
     reverses
    0.39
     aurait
    0.39
    Activations Density 0.153%

    No Known Activations