© 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. 0-CLT-HP
    7. 39911
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    ly
    -0.72
    dis
    -0.59
    das
    -0.57
    GS
    -0.57
    lys
    -0.55
    dar
    -0.54
    amo
    -0.54
    bas
    -0.53
    dc
    -0.52
    lou
    -0.51
    POSITIVE LOGITS
    TagMode
    1.28
    setVerticalGroup
    1.27
     ویکی‌پدیا
    1.24
    MemoryWarning
    1.20
     EconPapers
    1.17
    StoryboardSegue
    1.16
     ostavi
    1.15
    GEBURTSDATUM
    1.13
    ImageContext
    1.10
    OGND
    1.08
    Activations Density 0.285%

    No Known Activations