© 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. 4-CLT-HP
    4. 3108
    Prev
    Next
    INDEX
    Explanations

    silicon

    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
    gonic
    -0.75
    IndentedString
    -0.69
    latego
    -0.65
     EconPapers
    -0.64
    "])){
    -0.61
    =?";
    -0.60
    "){
    
    -0.60
    $.
    
    -0.59
    ")){
    
    -0.59
     ProtoMessage
    -0.59
    POSITIVE LOGITS
    #+#
    0.43
     features
    0.37
     accru
    0.37
     funerals
    0.36
     conductance
    0.34
     splen
    0.34
    BeforeMethod
    0.34
    rophi
    0.34
     withRouter
    0.34
     leases
    0.34
    Activations Density 0.004%

    No Known Activations