© 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. 20-CLT-HP
    7. 75193
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     صوتيه
    -0.60
    
    -0.59
    })*/
    -0.57
     ModelExpression
    -0.56
     wind
    -0.56
     winds
    -0.56
    Wind
    -0.54
     Wind
    -0.53
     createState
    -0.52
     Sélectionnez
    -0.52
    POSITIVE LOGITS
    trun
    0.55
    LONG
    0.50
    청
    0.50
     AssemblyTitle
    0.50
     الاطلاع
    0.50
    انگلیسی
    0.49
     LONG
    0.48
    byter
    0.48
    wpi
    0.47
    toBeTruthy
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.