© 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. 10326
    Prev
    Next
    INDEX
    Explanations

    including

    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
    GEBURTSDATUM
    -0.90
    webElementXpaths
    -0.84
    ScopeManager
    -0.69
    +#+#
    -0.69
     propOrder
    -0.62
    UnusedPrivate
    -0.59
    ]")]
    -0.59
    MigrationBuilder
    -0.58
    sizeCache
    -0.57
    Искәрмәләр
    -0.56
    POSITIVE LOGITS
     through
    1.04
     by
    0.92
     in
    0.86
     via
    0.83
     on
    0.77
     because
    0.74
     during
    0.73
     from
    0.72
    through
    0.71
     poprzez
    0.71
    Activations Density 0.035%

    No Known Activations