© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41891
    Prev
    Next
    INDEX
    Explanations

    design and biotechnology

    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
    Designer
    -0.90
     Designer
    -0.79
     designer
    -0.74
     Monfieur
    -0.74
    designer
    -0.70
     coupable
    -0.69
     inhabitants
    -0.69
     propOrder
    -0.66
    Architect
    -0.64
    BagLayout
    -0.64
    POSITIVE LOGITS
    '],$
    0.53
    ")->
    0.52
    IUrlHelper
    0.51
     res
    0.49
    ']=$
    0.47
    )_/¯
    0.46
    )[
    0.46
    ']?>
    0.46
    ures
    0.46
    LinkId
    0.45
    Activations Density 0.115%

    No Known Activations