© 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. 0-CLT-HP
    7. 2034
    Prev
    Next
    INDEX
    Explanations

    shampoo

    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
     marins
    -0.59
     fallu
    -0.55
     Jurí
    -0.54
     Ngb
    -0.54
     marinho
    -0.53
     margins
    -0.53
    thood
    -0.52
     UNEP
    -0.52
    mar
    -0.51
     distanza
    -0.51
    POSITIVE LOGITS
    ата
    0.55
     Statement
    0.54
     Pole
    0.52
    WebElementEntity
    0.52
    expandindo
    0.52
    peza
    0.51
    comers
    0.51
    orni
    0.50
    ought
    0.50
    InstanceState
    0.49
    Activations Density 0.396%

    No Known Activations