© 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. 9720
    Prev
    Next
    INDEX
    Explanations

    English language/grammar

    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
    mybatisplus
    -0.74
    principalTable
    -0.61
    ConstraintMaker
    -0.61
    Autoritní
    -0.59
     متعلقه
    -0.58
    openzeppelin
    -0.55
    Brainz
    -0.54
    aarrggbb
    -0.52
    NewUrlParser
    -0.52
     StatefulWidget
    -0.50
    POSITIVE LOGITS
    ReusableCell
    0.54
     hiér
    0.52
     Belajar
    0.50
     lexic
    0.49
    ]-->
    0.48
    SequentialGroup
    0.47
    Scénario
    0.47
     köl
    0.46
    lerc
    0.46
     écrite
    0.45
    Activations Density 0.010%

    No Known Activations