© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75400
    Prev
    Next
    INDEX
    Explanations

    adverbs

    np_max-act-logits · 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
    msgSender
    -0.59
    aarrggbb
    -0.54
     للمعارف
    -0.53
    NamedQueries
    -0.51
    DispatchToProps
    -0.50
    ftagPool
    -0.50
    ReusableCell
    -0.50
     Italijani
    -0.50
     siedz
    -0.48
    NameInMap
    -0.48
    POSITIVE LOGITS
     practically
    0.71
     ethically
    0.70
     globally
    0.68
     justly
    0.66
     Practically
    0.65
     Globally
    0.65
     internationally
    0.64
     fairly
    0.63
     across
    0.62
     well
    0.60
    Activations Density 0.003%

    No Known Activations