© 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. 1-CLT-HP
    4. 13307
    Prev
    Next
    INDEX
    Explanations

    Code/chemical data fragments

    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
     myco
    -0.78
    CopyWith
    -0.69
    ollectionView
    -0.59
    itanya
    -0.57
    MemoryWarning
    -0.56
    ayer
    -0.54
    ResponseWriter
    -0.52
    ftagPool
    -0.52
     TextStyle
    -0.52
    ungszeit
    -0.50
    POSITIVE LOGITS
     bénéficiaire
    0.50
    <bos>
    0.48
    Là
    0.48
     disponibilités
    0.47
     Kär
    0.47
    zeptember
    0.46
    utoff
    0.46
    issipp
    0.45
    feitura
    0.45
    NonQuery
    0.44
    Activations Density 0.022%

    No Known Activations