© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 966
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    InputBorder
    -0.73
     BoxDecoration
    -0.63
     nakalista
    -0.62
    addCriterion
    -0.60
     Paglinawan
    -0.57
     AssemblyTitle
    -0.56
     nearby
    -0.56
     Савезне
    -0.54
    Hentet
    -0.54
    __':
    -0.53
    POSITIVE LOGITS
    ihnachten
    0.49
    الحياه
    0.48
    MigrationBuilder
    0.46
    PRNewswire
    0.46
    createCanvas
    0.45
    bronn
    0.44
     who
    0.44
    cheid
    0.44
     FormData
    0.43
    alyptus
    0.43
    Activations Density 0.001%

    No Known Activations