© 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. 10944
    Prev
    Next
    INDEX
    Explanations

    fiber optics

    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
    cupertino
    -0.50
    cham
    -0.43
    char
    -0.43
    ([
    -0.41
    onz
    -0.41
    ua
    -0.41
    JspWriter
    -0.40
    che
    -0.40
    ściu
    -0.38
    poke
    -0.38
    POSITIVE LOGITS
    DockStyle
    0.78
    日閲覧
    0.76
    出版年
    0.75
     nôtre
    0.72
     étoient
    0.68
     jambes
    0.67
     avoient
    0.66
     épaules
    0.66
     ujednoznacz
    0.65
    EDEFAULT
    0.65
    Activations Density 0.052%

    No Known Activations