© 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. 0-CLT-HP
    7. 40538
    Prev
    Next
    INDEX
    Explanations

    positions (physical/temporal)

    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
    TagHelper
    -0.61
    IBOutlet
    -0.57
     estimés
    -0.56
    ثيق
    -0.56
     Chwiliwch
    -0.53
    OrBuilder
    -0.51
    ogne
    -0.50
    hene
    -0.48
    itious
    -0.48
    ipot
    -0.47
    POSITIVE LOGITS
     of
    1.40
    of
    0.64
     line
    0.57
     Administrativna
    0.54
    mybatisplus
    0.54
    ของ
    0.53
     half
    0.52
     của
    0.51
     olímp
    0.50
    OfWork
    0.50
    Activations Density 0.089%

    No Known Activations