© 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. 0-CLT-HP
    7. 94550
    Prev
    Next
    INDEX
    Explanations

    changing, stopping

    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
     igång
    -0.79
     larmes
    -0.72
     noires
    -0.69
     ouvertes
    -0.69
     extérieures
    -0.69
     fidèles
    -0.67
     chré
    -0.66
     vectorielles
    -0.66
     sœurs
    -0.65
     religieuses
    -0.65
    POSITIVE LOGITS
     the
    1.54
     their
    1.08
     a
    1.02
     its
    1.01
     those
    1.00
     some
    0.97
     our
    0.96
     your
    0.94
     these
    0.90
     any
    0.88
    Activations Density 0.019%

    No Known Activations