© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4729
    Prev
    Next
    INDEX
    Explanations

    issue

    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
    -0.69
    eclampsia
    -0.52
     Stirn
    -0.50
     réponses
    -0.48
    الإنجليزية
    -0.48
    chluss
    -0.48
     nevoie
    -0.48
    HtmlAttribute
    -0.48
     bisogno
    -0.48
     Viitattu
    -0.48
    POSITIVE LOGITS
    ensement
    0.63
    tvguidetime
    0.62
    
    0.58
     betweenstory
    0.54
    aarrggbb
    0.52
    gameserver
    0.50
     utafitiHapana
    0.50
    Autoritní
    0.50
    usermodel
    0.49
    StackNavigator
    0.47
    Activations Density 0.002%

    No Known Activations