© 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. 4-CLT-HP
    7. 1840
    Prev
    Next
    INDEX
    Explanations

    for

    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
     MainAxisSize
    -0.73
    SequentialGroup
    -0.67
     Dangers
    -0.60
    BeginContext
    -0.59
     conjectures
    -0.57
     CreateTagHelper
    -0.57
     Hopes
    -0.56
     hopes
    -0.55
     hurdles
    -0.54
     craindre
    -0.54
    POSITIVE LOGITS
    later
    0.57
     later
    0.55
     further
    0.52
     change
    0.51
     continued
    0.51
     
    0.50
    后来
    0.50
    further
    0.49
    gume
    0.48
    graphers
    0.47
    Activations Density 0.009%

    No Known Activations