© 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. 5-CLT-HP
    7. 120
    Prev
    Next
    INDEX
    Explanations

    article "a" or "an"

    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
     calendriers
    -0.69
     invokingState
    -0.67
     contextLoads
    -0.66
    sidemargin
    -0.64
    chaic
    -0.60
    曖昧さ回避
    -0.59
    errHandler
    -0.58
    isome
    -0.58
    Externí
    -0.57
    twimg
    -0.57
    POSITIVE LOGITS
     list
    0.56
     final
    0.56
     كومونز
    0.48
     report
    0.46
     Final
    0.45
    ListItemIcon
    0.44
     profile
    0.44
     set
    0.43
     wealth
    0.43
    StackNavigator
    0.43
    Activations Density 0.002%

    No Known Activations