© 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. 0-CLT-HP
    7. 97275
    Prev
    Next
    INDEX
    Explanations

    reading and writing

    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
     fédé
    -0.68
     bianche
    -0.61
    MigrationBuilder
    -0.59
    HtmlAttribute
    -0.59
    ode
    -0.59
     quæ
    -0.59
     uș
    -0.59
     Having
    -0.58
     presidency
    -0.58
     noires
    -0.56
    POSITIVE LOGITS
     UnityEditor
    0.59
     Vella
    0.52
    互联网档案馆
    0.52
     '
    0.52
    ucine
    0.50
    SuppressMessage
    0.49
    bcryptjs
    0.49
     True
    0.49
    StateToProps
    0.49
    AllAfrica
    0.47
    Activations Density 0.172%

    No Known Activations