© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10014
    Prev
    Next
    INDEX
    Explanations

    introductions and advertisements

    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
    Introductory
    -0.81
     Introductory
    -0.80
    INTRODUCTION
    -0.63
    preter
    -0.60
     introductory
    -0.59
     Biôgrafia
    -0.56
    titleMargin
    -0.54
    enment
    -0.54
    </caption>
    -0.54
     INTRODUCTION
    -0.54
    POSITIVE LOGITS
     насељу
    0.57
    المناصب
    0.55
     AutoMapper
    0.48
    OGND
    0.46
    assertAll
    0.46
    MENAFN
    0.46
    concentration
    0.46
    وفاته
    0.45
    الإنجليزية
    0.45
    Usos
    0.44
    Activations Density 0.086%

    No Known Activations