© 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. 4-CLT-HP
    7. 2734
    Prev
    Next
    INDEX
    Explanations

    function words and numbers

    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
     RouterModule
    -0.57
     based
    -0.56
    endpush
    -0.54
     [*]
    -0.54
     Based
    -0.54
    endphp
    -0.53
     BASED
    -0.52
    mobileqq
    -0.52
    Based
    -0.52
     combineReducers
    -0.52
    POSITIVE LOGITS
    UnsafeEnabled
    0.65
    expandindo
    0.57
     Commencez
    0.54
    ionario
    0.54
     niech
    0.52
    Abit
    0.51
    archiviato
    0.50
     czyn
    0.50
    item
    0.49
    icidio
    0.48
    Activations Density 0.007%

    No Known Activations