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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96899
    Prev
    Next
    INDEX
    Explanations

    the

    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
    BeginContext
    -0.59
     motivadoras
    -0.55
     sauvages
    -0.50
     químico
    -0.49
     modernas
    -0.48
     dessus
    -0.48
     fidé
    -0.48
     Orrell
    -0.47
    ParallelGroup
    -0.47
    ̣t
    -0.47
    POSITIVE LOGITS
     jLabel
    0.66
    TypedDataSet
    0.61
    jsonwebtoken
    0.59
     jScrollPane
    0.57
    +#+#
    0.57
     itemprop
    0.56
     InputDecoration
    0.55
     eventdata
    0.55
    amqp
    0.55
     насеља
    0.55
    Activations Density 0.002%

    No Known Activations