© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13667
    Prev
    Next
    INDEX
    Explanations

    arily

    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
     autorytatywna
    -0.93
     lenker
    -0.71
    SharedCtor
    -0.69
    Jeografia
    -0.67
     Spinoza
    -0.66
    expandindo
    -0.66
    andoah
    -0.65
     الرياضيه
    -0.63
    Erreferentziak
    -0.62
    n
    -0.61
    POSITIVE LOGITS
    makeConstraints
    0.50
    lizes
    0.49
    lise
    0.45
    oru
    0.42
     excuse
    0.42
    lized
    0.42
    ente
    0.42
     blame
    0.41
    liz
    0.41
    lida
    0.40
    Activations Density 0.028%

    No Known Activations