© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45510
    Prev
    Next
    INDEX
    Explanations

    changes being reflected

    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
     embodied
    -0.61
     Administrativna
    -0.59
     reflected
    -0.58
     acknowledges
    -0.57
     pylori
    -0.56
    FormTagHelper
    -0.50
     puns
    -0.49
     philosophy
    -0.49
     оригіналу
    -0.48
     absorbed
    -0.48
    POSITIVE LOGITS
    EDEFAULT
    0.71
    تقاوى
    0.69
     élas
    0.66
    AutoField
    0.57
    IUrlHelper
    0.57
    lained
    0.56
    ///</
    0.52
    AsStream
    0.52
    IndentedString
    0.52
    Gemeinden
    0.52
    Activations Density 0.042%

    No Known Activations