© 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. 10716
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
     centuries
    -1.44
     Centuries
    -0.96
    urers
    -0.89
     millennia
    -0.88
    CloseOperation
    -0.76
    tôi
    -0.74
     siècles
    -0.74
     siglos
    -0.72
     CURIAM
    -0.68
     generations
    -0.68
    POSITIVE LOGITS
     L
    0.50
    .
    0.49
     Phase
    0.49
    setVerticalGroup
    0.49
    ールド
    0.44
     V
    0.44
    يميديا
    0.43
    ,
    0.43
     Array
    0.41
     K
    0.40
    Activations Density 0.052%

    No Known Activations