© 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. 0-CLT-HP
    4. 42446
    Prev
    Next
    INDEX
    Explanations

    zero

    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
     الحره
    -1.01
    ]--;
    -0.98
    ViewFeatures
    -0.98
     ?>>
    -0.82
    )";
    
    -0.79
    __':
    
    -0.79
    Erreferentziak
    -0.78
     resourceCulture
    -0.76
     }}}{
    -0.76
    FTFY
    -0.76
    POSITIVE LOGITS
    0
    0.76
    s
    0.75
    m
    0.63
    k
    0.63
    th
    0.62
    8
    0.62
     to
    0.58
    km
    0.57
    1
    0.57
    K
    0.56
    Activations Density 0.077%

    No Known Activations