© 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. 73195
    Prev
    Next
    INDEX
    Explanations

    PRE

    np_max-act-logits · 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
    oneofs
    -0.68
     autorytatywna
    -0.67
     &___
    -0.63
     AssemblyTitle
    -0.60
    Autoritní
    -0.59
    ագրություններ
    -0.57
     EconPapers
    -0.56
    createClass
    -0.55
    æder
    -0.55
     Chef
    -0.54
    POSITIVE LOGITS
    AndEndTag
    0.71
     noqa
    0.59
    BagLayout
    0.58
    NameInMap
    0.55
     Parenthood
    0.48
    kop
    0.46
    StoryboardSegue
    0.45
    vente
    0.44
    kiye
    0.43
    Jîn
    0.42
    Activations Density 0.003%

    No Known Activations