© 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. 20-CLT-HP
    7. 72973
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -0.89
    Geplaatst
    -0.72
     дописавши
    -0.59
    GEBURTSDATUM
    -0.59
     {?>
    -0.56
    مصادر
    -0.56
    BagLayout
    -0.56
     ComVisible
    -0.52
    はじめに
    -0.52
    ]<<"
    -0.52
    POSITIVE LOGITS
    כט
    0.58
    abetes
    0.57
    AndEndTag
    0.56
    bootstrapcdn
    0.54
    jamos
    0.54
    Arc
    0.52
    ächtige
    0.52
     haem
    0.51
    Boa
    0.50
     CRU
    0.50
    Activations Density 0.005%

    No Known Activations