© 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. 92106
    Prev
    Next
    INDEX
    Explanations

    programming/ tech

    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
     Administrativna
    -0.64
    
    -0.59
    thâu
    -0.59
    ఔ
    -0.56
     positifs
    -0.56
    webElementXpaths
    -0.54
    adomo
    -0.52
     leſs
    -0.52
     Jefus
    -0.51
     purpoſe
    -0.49
    POSITIVE LOGITS
    
    0.65
     invokingState
    0.55
     balanceOf
    0.54
    initComponents
    0.53
    ecore
    0.52
     يتيمه
    0.52
     оригіналу
    0.50
    Datuak
    0.50
    tagHelperRunner
    0.50
     taken
    0.50
    Activations Density 0.002%

    No Known Activations