© 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. 15740
    Prev
    Next
    INDEX
    Explanations

    the

    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
    NOPQRST
    -0.55
     chré
    -0.52
     enfans
    -0.50
     avoient
    -0.50
     tertinggi
    -0.49
     tormenta
    -0.48
    MemoryWarning
    -0.47
     religieuses
    -0.47
     snippetHide
    -0.47
     kabát
    -0.47
    POSITIVE LOGITS
     enzyme
    0.60
     mammalian
    0.59
     biologic
    0.58
     subd
    0.57
     adrenal
    0.56
     pathogenesis
    0.56
     intersti
    0.55
     my
    0.55
     xanth
    0.54
     axons
    0.54
    Activations Density 0.016%

    No Known Activations