© 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. 94418
    Prev
    Next
    INDEX
    Explanations

    choices and options

    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
     purpoſe
    -0.72
     himſelf
    -0.72
     themſelves
    -0.63
     Jefus
    -0.63
     itſelf
    -0.63
     pleaſure
    -0.63
     cauſe
    -0.63
     "..\..\..\
    -0.63
     estimés
    -0.62
     preparation
    -0.59
    POSITIVE LOGITS
    AnchorStyles
    0.63
    RenderAtEndOf
    0.63
    tvguidetime
    0.62
    новништво
    0.61
     المعيارى
    0.61
    webElement
    0.60
    AddHtmlAttribute
    0.60
     препратки
    0.59
     مرئيه
    0.58
    AddTagHelper
    0.57
    Activations Density 0.038%

    No Known Activations