© 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. 5-CLT-HP
    7. 91383
    Prev
    Next
    INDEX
    Explanations

    shooting

    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
    Билгалдахарш
    -0.52
     agonists
    -0.52
     conversions
    -0.52
     fillings
    -0.50
     easement
    -0.50
     biomarkers
    -0.49
     automata
    -0.48
     jumpers
    -0.48
     epics
    -0.47
     parasites
    -0.47
    POSITIVE LOGITS
     AssemblyProduct
    0.64
     @"/
    0.62
    addPreferredGap
    0.61
    }_\
    0.60
    ,‎
    0.56
    )}_
    0.55
    ſcher
    0.54
     متعلقه
    0.54
    %</
    0.52
    /</
    0.52
    Activations Density 0.039%

    No Known Activations