© 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. 1-CLT-HP
    7. 12497
    Prev
    Next
    INDEX
    Explanations

    cause

    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
     Chwiliwch
    -1.03
    GEBURTSDATUM
    -0.99
    TypedDataSet
    -0.96
     المعيارى
    -0.91
    ThroughAttribute
    -0.89
    WriteTagHelper
    -0.87
    ArrowToggle
    -0.85
     виправивши
    -0.81
     للمعارف
    -0.77
    WebElementEntity
    -0.77
    POSITIVE LOGITS
     traseiro
    0.41
     adesivo
    0.38
    öße
    0.38
     gezondheid
    0.38
     cojín
    0.38
     devaient
    0.38
     comentário
    0.37
    arai
    0.36
    ou
    0.36
     fat
    0.36
    Activations Density 0.044%

    No Known Activations