© 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. 45075
    Prev
    Next
    INDEX
    Explanations

    co

    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
     co
    -0.92
    ly
    -0.85
    less
    -0.67
    了
    -0.66
    nya
    -0.66
    に
    -0.63
    mente
    -0.60
    fully
    -0.57
     den
    -0.56
    是
    -0.56
    POSITIVE LOGITS
     NSCoder
    0.78
    TagMode
    0.71
     surla
    0.67
     responsabilità
    0.65
     otomatig
    0.65
    >{@
    0.61
     Савезне
    0.56
     <>",
    0.55
     يتيمه
    0.54
     PLWABN
    0.54
    Activations Density 0.288%

    No Known Activations