© 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. 76796
    Prev
    Next
    INDEX
    Explanations

    random proper nouns and code

    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
     vícti
    -0.59
     Malle
    -0.59
    ########.
    -0.55
     intValue
    -0.54
    MessageTagHelper
    -0.51
     imple
    -0.50
     Commit
    -0.48
     ujednoznacz
    -0.48
     Obra
    -0.47
    mability
    -0.47
    POSITIVE LOGITS
    RectangleBorder
    0.60
     "..\..\
    0.59
    oa̍t
    0.58
    fortawesome
    0.58
    PageContext
    0.57
    igshid
    0.57
    myspace
    0.56
     FishBase
    0.55
    ecore
    0.51
     noastre
    0.50
    Activations Density 0.023%

    No Known Activations