© 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. 96975
    Prev
    Next
    INDEX
    Explanations

    as

    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
    Kapcsolódó
    -0.48
    ENAME
    -0.48
     udaler
    -0.46
    indelijk
    -0.46
     interest
    -0.45
    OWN
    -0.44
     negative
    -0.42
     trách
    -0.41
     interesse
    -0.41
     foglal
    -0.41
    POSITIVE LOGITS
    __":
    0.78
    AnimationsModule
    0.77
    __':
    0.75
    
    0.75
    RectangleBorder
    0.70
     المعيارى
    0.69
     ExecuteAsync
    0.67
     للمعارف
    0.67
     saites
    0.65
    Odkazy
    0.65
    Activations Density 0.002%

    No Known Activations