© 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. 96211
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    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
    findpost
    -0.74
    oa̍t
    -0.67
     AssemblyProduct
    -0.62
    tispiece
    -0.61
     pyplot
    -0.61
    ChildIndex
    -0.60
     rowspan
    -0.59
     isSet
    -0.57
     otomatig
    -0.54
    ranslated
    -0.54
    POSITIVE LOGITS
     may
    0.86
     can
    0.62
    may
    0.59
     shall
    0.56
     will
    0.53
     Может
    0.52
     might
    0.51
     Peut
    0.50
     cannot
    0.48
     может
    0.48
    Activations Density 0.001%

    No Known Activations