© 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. 44037
    Prev
    Next
    INDEX
    Explanations

    exploration and ambition

    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
    bootstrapcdn
    -0.76
    CloseOperation
    -0.69
    RectangleBorder
    -0.68
     TextInputType
    -0.67
     abstrait
    -0.65
    HomeAsUpEnabled
    -0.65
     démocr
    -0.61
    最快更新
    -0.60
    abetes
    -0.60
     automatiques
    -0.60
    POSITIVE LOGITS
    <bos>
    0.94
     for
    0.67
    NameInMap
    0.59
    ⓧ
    0.59
    getDescriptor
    0.54
    bParam
    0.51
     Sin
    0.50
     Good
    0.48
    RegressionTest
    0.47
     to
    0.46
    Activations Density 0.054%

    No Known Activations