© 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. 5697
    Prev
    Next
    INDEX
    Explanations

    math/statistics

    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
    addPreferredGap
    -0.51
    RequiresApi
    -0.45
    ędz
    -0.44
    央
    -0.42
     caché
    -0.41
    tų
    -0.41
     bono
    -0.40
     Undeclared
    -0.40
    FailureListener
    -0.40
     CURIAM
    -0.39
    POSITIVE LOGITS
    SBATCH
    0.67
    Jereo
    0.64
     ErrIntOverflow
    0.63
     nahilalakip
    0.62
    ]<=
    0.62
     ModelExpression
    0.61
     ویکی‌پدی
    0.59
    RegressionTest
    0.59
    fillType
    0.58
     Comprometido
    0.57
    Activations Density 0.009%

    No Known Activations