© 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. 0-CLT-HP
    7. 41582
    Prev
    Next
    INDEX
    Explanations

    supernova

    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
    ValueStyle
    -0.78
     beyond
    -0.76
     MonoBehaviour
    -0.69
    beyond
    -0.69
    aarrggbb
    -0.68
    ReusableCell
    -0.64
     BEYOND
    -0.63
    ItemBackground
    -0.63
    +#+#
    -0.63
     réguli
    -0.62
    POSITIVE LOGITS
    e
    0.69
    s
    0.69
    tur
    0.59
    i
    0.59
    ed
    0.57
    k
    0.55
     the
    0.55
    a
    0.55
    ming
    0.54
    ep
    0.52
    Activations Density 1.489%

    No Known Activations