© 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. 4-CLT-HP
    7. 74
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
     defStyleAttr
    -0.65
    Datuak
    -0.54
    windowFixed
    -0.54
    yarnpkg
    -0.53
    toMatchSnapshot
    -0.52
    piram
    -0.52
     to
    -0.50
    المكان
    -0.49
     correctes
    -0.48
     calloc
    -0.48
    POSITIVE LOGITS
     of
    0.72
     locations
    0.61
     places
    0.58
     của
    0.57
     areas
    0.56
     betweenstory
    0.56
     venues
    0.49
     lugares
    0.49
    environments
    0.49
    spesies
    0.49
    Activations Density 0.002%

    No Known Activations