© 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. 5-CLT-HP
    7. 91959
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     useStyles
    -0.59
     nahilalakip
    -0.58
    omiast
    -0.57
    igshid
    -0.57
     ddelweddau
    -0.52
     Viceroy
    -0.52
    ệu
    -0.50
    essed
    -0.50
     vaccinated
    -0.50
    DrawerToggle
    -0.50
    POSITIVE LOGITS
     planning
    0.79
    BeginContext
    0.66
    Planning
    0.62
    Rüyada
    0.60
    planning
    0.60
     PLANNING
    0.58
     Planning
    0.57
     plan
    0.57
    HtmlAttribute
    0.56
     planners
    0.53
    Activations Density 0.001%

    No Known Activations