© 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. 15829
    Prev
    Next
    INDEX
    Explanations

    therapy, chromatography

    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
    AndEndTag
    -1.29
     betweenstory
    -1.21
    ArrowToggle
    -1.05
    GEBURTSDATUM
    -1.04
     OFDb
    -1.01
    ConstraintMaker
    -0.99
    AddTagHelper
    -0.95
     '\\;'
    -0.94
     lenker
    -0.89
    CloseOperation
    -0.88
    POSITIVE LOGITS
    ed
    0.66
    edi
    0.61
    y
    0.57
    sus
    0.56
     Sus
    0.51
    ies
    0.51
    Sus
    0.51
     di
    0.51
    abi
    0.51
    in
    0.50
    Activations Density 0.171%

    No Known Activations