© 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. 2600
    Prev
    Next
    INDEX
    Explanations

    are

    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
    MigrationBuilder
    -0.82
    GEBURTSDATUM
    -0.69
     contextLoads
    -0.65
     Chwiliwch
    -0.64
     the
    -0.60
    WebServlet
    -0.58
     /(\
    -0.55
     виправивши
    -0.54
     coronation
    -0.54
    TintMode
    -0.54
    POSITIVE LOGITS
     חיצוניים
    0.58
     called
    0.55
     referred
    0.53
     fallu
    0.52
     bedoeld
    0.50
     kalt
    0.48
     termed
    0.47
     beroep
    0.46
     meant
    0.46
    classed
    0.44
    Activations Density 0.001%

    No Known Activations