© 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. 0-CLT-HP
    7. 94461
    Prev
    Next
    INDEX
    Explanations

    adverbs of degree/uncertainty

    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
     the
    -0.74
     a
    -0.62
     
    -0.51
     all
    -0.50
     some
    -0.50
     what
    -0.48
     their
    -0.46
     an
    -0.45
     sometimes
    -0.45
     maybe
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.94
    tagHelperRunner
    0.91
     autorytatywna
    0.90
    rungsseite
    0.89
     calendriers
    0.89
     defaultstate
    0.87
     ujednoznacz
    0.87
     désolés
    0.85
    windowFixed
    0.85
     виправивши
    0.84
    Activations Density 0.029%

    No Known Activations