© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46328
    Prev
    Next
    INDEX
    Explanations

    ad

    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
     Meksiku
    -0.67
    SequentialGroup
    -0.67
    verwijspagina
    -0.57
     chré
    -0.54
     تضيفلها
    -0.54
    SerializedSize
    -0.53
     conseguenza
    -0.52
    RenderAtEndOf
    -0.51
     extérieure
    -0.51
     Grecs
    -0.50
    POSITIVE LOGITS
    <bos>
    0.65
    GEBURTSDATUM
    0.61
    ViewFeatures
    0.58
    SharedDtor
    0.57
     sitting
    0.54
    localctx
    0.53
    المشاركات
    0.53
    Portail
    0.52
     squatting
    0.52
    elf
    0.51
    Activations Density 0.012%

    No Known Activations