© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75702
    Prev
    Next
    INDEX
    Explanations

    San

    np_max-act-logits · 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
     NotImplemented
    -0.42
     vuitton
    -0.42
     consultation
    -0.41
    banen
    -0.40
     consulta
    -0.40
     alt
    -0.40
    💼
    -0.40
     Illuminate
    -0.40
     invers
    -0.39
    Jîn
    -0.39
    POSITIVE LOGITS
    JspWriter
    0.69
     BorderRadius
    0.67
    TagMode
    0.62
    arraycopy
    0.62
    ArgumentParser
    0.62
    SourceChecksum
    0.60
    ScopeManager
    0.59
    ContentAsync
    0.57
    MigrationBuilder
    0.57
    ="@+
    0.56
    Activations Density 0.001%

    No Known Activations