© 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. 0-CLT-HP
    7. 43040
    Prev
    Next
    INDEX
    Explanations

    study

    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
    sidemargin
    -0.68
    bing
    -0.66
    addContainerGap
    -0.64
     study
    -0.63
     cherchés
    -0.62
    Study
    -0.61
     Study
    -0.60
    =$?
    -0.60
    TestingModule
    -0.56
     Spisak
    -0.55
    POSITIVE LOGITS
    PerformLayout
    0.63
     ſte
    0.61
     ſtate
    0.55
     فريبيس
    0.55
     ſy
    0.54
    存于互联网档案馆
    0.54
     iſt
    0.53
     ſch
    0.52
     ſol
    0.52
     unſ
    0.52
    Activations Density 0.175%

    No Known Activations