© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9285
    Prev
    Next
    INDEX
    Explanations

    read

    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
    ies
    -0.49
     "
    -0.48
    AGING
    -0.47
    Est
    -0.46
    ses
    -0.46
    en
    -0.46
    Scroll
    -0.46
    νομ
    -0.45
    esson
    -0.45
     horn
    -0.45
    POSITIVE LOGITS
     estekak
    0.84
     متعلقه
    0.81
     désolés
    0.78
     disambiguazione
    0.69
    uação
    0.68
    +#+#
    0.65
     lenker
    0.64
     <=",
    0.63
    êque
    0.63
    elfth
    0.62
    Activations Density 0.035%

    No Known Activations