© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2355
    Prev
    Next
    INDEX
    Explanations

    coding environments

    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
    <bos>
    -0.67
     renovables
    -0.47
     å
    -0.45
     complètes
    -0.45
    тч
    -0.44
     AssemblyCulture
    -0.44
     nisso
    -0.44
     Farms
    -0.43
     avanti
    -0.43
     Push
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.79
     defaultstate
    0.76
     MainAxisSize
    0.72
     EconPapers
    0.70
     Numerade
    0.69
    protoimpl
    0.67
    SequentialGroup
    0.66
     يتيمه
    0.66
     InputDecoration
    0.64
    WindowConstants
    0.64
    Activations Density 0.028%

    No Known Activations