© 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. 45259
    Prev
    Next
    INDEX
    Explanations

    write

    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
     write
    -1.04
    write
    -0.92
     Write
    -0.85
    Write
    -0.80
    setVerticalGroup
    -0.79
     resourceCulture
    -0.78
    UnusedPrivate
    -0.77
     nakalista
    -0.77
     WRITE
    -0.70
    read
    -0.64
    POSITIVE LOGITS
     great
    0.59
    anguard
    0.52
    četně
    0.50
    างเกง
    0.49
     δὲ
    0.48
    prefixer
    0.48
     accurate
    0.47
    ürlich
    0.47
    Accurate
    0.47
    crombie
    0.47
    Activations Density 0.021%

    No Known Activations