© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95130
    Prev
    Next
    INDEX
    Explanations

    Punctuation and Code

    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
     pinulongan
    -0.67
    addCriterion
    -0.61
     propOrder
    -0.60
    WriteBarrier
    -0.59
    invokeLater
    -0.59
     wireType
    -0.59
     adicionais
    -0.57
     noqa
    -0.57
     referenties
    -0.56
    djangoproject
    -0.54
    POSITIVE LOGITS
    <bos>
    0.97
     though
    0.60
    though
    0.56
     nhất
    0.52
     the
    0.50
    Though
    0.50
     THOUGH
    0.49
     jednak
    0.48
     Though
    0.48
     otomatig
    0.48
    Activations Density 0.000%

    No Known Activations