© 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. 98036
    Prev
    Next
    INDEX
    Explanations

    lead

    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
     retraite
    -0.48
     tű
    -0.48
     impegn
    -0.46
    Encounter
    -0.46
    aih
    -0.45
    Reverse
    -0.45
    før
    -0.45
    ???:
    -0.45
    lji
    -0.45
    ália
    -0.45
    POSITIVE LOGITS
     invariably
    0.78
    Datuak
    0.70
     estekak
    0.69
     typically
    0.68
     oftentimes
    0.68
     inevitably
    0.68
     usually
    0.65
     normally
    0.62
     often
    0.60
     Typically
    0.59
    Activations Density 0.002%

    No Known Activations