© 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. 9376
    Prev
    Next
    INDEX
    Explanations

    man

    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
    tagHelperRunner
    -0.52
     Judd
    -0.52
     Zorg
    -0.46
    duga
    -0.45
     Yugoslavia
    -0.45
     identification
    -0.45
    PARATUS
    -0.44
    FormTagHelper
    -0.43
     identified
    -0.42
    skem
    -0.42
    POSITIVE LOGITS
    SharedDtor
    0.83
     Мексичка
    0.58
    ingale
    0.57
    ้อมูล
    0.55
     NSCoder
    0.54
    verwijspagina
    0.52
     hym
    0.52
     endforeach
    0.50
    AccessorTable
    0.50
     >=",
    0.50
    Activations Density 0.005%

    No Known Activations