© 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. 2804
    Prev
    Next
    INDEX
    Explanations

    Code/documentation 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
    cshtml
    -0.75
    üyada
    -0.68
    पया
    -0.67
    getMenuInflater
    -0.66
    >>()
    -0.64
     doInBackground
    -0.59
    IUrlHelper
    -0.58
    ########.
    -0.58
     resourceCulture
    -0.57
    crollView
    -0.56
    POSITIVE LOGITS
     lccn
    0.48
     Diplomacy
    0.47
    Liefer
    0.46
     lopen
    0.44
    ukka
    0.44
    WinForms
    0.44
     Lordship
    0.43
    Protobuf
    0.43
     diplomacy
    0.42
    titleMargin
    0.42
    Activations Density 0.003%

    No Known Activations