© 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. 4931
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     AssemblyProduct
    -0.65
    BeginContext
    -0.62
     <<<<<<<<<<<<<<
    -0.52
    superuser
    -0.52
    Diweddarwch
    -0.50
     Karim
    -0.50
    ArgumentParser
    -0.50
    HttpException
    -0.49
     ECONOM
    -0.47
     lactic
    -0.47
    POSITIVE LOGITS
    otes
    0.76
    wolf
    0.68
    tone
    0.63
    wolves
    0.63
    tones
    0.62
    OTES
    0.61
    pu
    0.60
    dogs
    0.56
    Wolves
    0.52
    dog
    0.52
    Activations Density 0.000%

    No Known Activations