© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    degree adverbs

    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
     كومونز
    -0.91
    Personensuche
    -0.81
     مشين
    -0.80
     InputDecoration
    -0.79
    kloped
    -0.78
     виправивши
    -0.77
     obfer
    -0.74
    Vidite
    -0.73
     autorytatywna
    -0.71
     myſelf
    -0.71
    POSITIVE LOGITS
     a
    0.93
     an
    0.71
     the
    0.64
     some
    0.51
     that
    0.45
    springframework
    0.41
    AnimationsModule
    0.41
     लगा
    0.41
    ɫ
    0.40
     Fat
    0.40
    Activations Density 0.002%

    No Known Activations