© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 14575
    Prev
    Next
    INDEX
    Explanations

    people

    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
    AddTagHelper
    -1.16
     Мексичка
    -0.99
    enderror
    -0.96
     BorderRadius
    -0.91
     ModelExpression
    -0.88
     <=",
    -0.88
    ?
    
    -0.87
     AspNetCore
    -0.86
     AppColors
    -0.84
    DockStyle
    -0.84
    POSITIVE LOGITS
    a
    0.46
    all
    0.46
     shout
    0.45
     use
    0.42
     lo
    0.42
     brazos
    0.42
    path
    0.41
    of
    0.40
     of
    0.40
     olan
    0.38
    Activations Density 0.006%

    No Known Activations