© 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. 10508
    Prev
    Next
    INDEX
    Explanations

    footprint

    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
     footprint
    -0.83
     footprints
    -0.77
    ication
    -0.70
     iceberg
    -0.68
     sputnik
    -0.65
     propof
    -0.65
    illigen
    -0.64
     defaultstate
    -0.62
    WithMany
    -0.61
     Footprint
    -0.58
    POSITIVE LOGITS
    íslu
    0.60
     noqa
    0.58
    ing
    0.57
    ethe
    0.53
    ed
    0.52
    ized
    0.52
    으
    0.52
    ize
    0.51
     étan
    0.51
    ues
    0.50
    Activations Density 0.004%

    No Known Activations