© 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. 761
    Prev
    Next
    INDEX
    Explanations

    recommendations and support

    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
    DoubleQuotes
    -0.59
    OPTS
    -0.49
    rizona
    -0.47
    
    -0.46
    ⎩
    -0.46
    談社
    -0.44
    ospels
    -0.42
    die
    -0.42
    TagHelper
    -0.41
    uldade
    -0.41
    POSITIVE LOGITS
     numberOfRows
    0.72
     snippetHide
    0.66
    WithIOException
    0.65
     NSCoder
    0.58
     استنادى
    0.56
     onlyOwner
    0.56
    Cubit
    0.56
    writeFieldEnd
    0.55
    EDEFAULT
    0.54
     onCancelled
    0.54
    Activations Density 0.002%

    No Known Activations