© 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. 4-CLT-HP
    7. 1680
    Prev
    Next
    INDEX
    Explanations

    code, reviews, legal text

    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
     EconPapers
    -0.84
    AndEndTag
    -0.72
     intptr
    -0.70
    saraba
    -0.66
    routeProvider
    -0.64
    Tembelea
    -0.63
    therosclerosis
    -0.61
     InputDecoration
    -0.60
    Referanser
    -0.58
     дописавши
    -0.58
    POSITIVE LOGITS
     Gly
    0.49
     GL
    0.46
    ic
    0.46
     Exploit
    0.44
    icen
    0.42
    Lev
    0.42
    Gly
    0.42
    њу
    0.41
     Eier
    0.41
    ymce
    0.41
    Activations Density 0.003%

    No Known Activations