© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46260
    Prev
    Next
    INDEX
    Explanations

    of

    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
     كمان
    -0.50
    enggarakan
    -0.49
     gesehen
    -0.47
    TypedDataSet
    -0.47
    ecznie
    -0.46
     strana
    -0.45
     للمعارف
    -0.45
    sinki
    -0.44
    cade
    -0.44
    jasama
    -0.44
    POSITIVE LOGITS
     himself
    0.84
     yourself
    0.83
     herself
    0.82
     themselves
    0.79
    Personensuche
    0.77
    GEBURTSDATUM
    0.77
    expandindo
    0.73
     CreateTagHelper
    0.72
    RepeatedField
    0.69
     oneself
    0.68
    Activations Density 0.014%

    No Known Activations