© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97479
    Prev
    Next
    INDEX
    Explanations

    knee

    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
     knee
    -1.11
    knee
    -0.99
     Knee
    -0.88
     partially
    -0.81
     knees
    -0.77
     Partially
    -0.75
    Knee
    -0.73
    immediately
    -0.69
     immediately
    -0.69
    reportWebVitals
    -0.68
    POSITIVE LOGITS
     GenerationType
    0.58
     المعيارى
    0.57
    
    0.53
     sensitive
    0.52
     مرئيه
    0.51
    TEMPO
    0.51
    pager
    0.50
    alou
    0.49
     vera
    0.47
    unistd
    0.47
    Activations Density 0.136%

    No Known Activations