© 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. 71935
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific text

    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
    enterOuterAlt
    -0.58
    VIAF
    -0.54
     الحره
    -0.46
    ANE
    -0.46
    andidate
    -0.45
    ACJA
    -0.44
     pry
    -0.44
     statistique
    -0.44
     Administrative
    -0.43
    fml
    -0.43
    POSITIVE LOGITS
     ujednoznacz
    0.73
     Efq
    0.59
     HasFactory
    0.54
     AssemblyTitle
    0.54
     raiſ
    0.52
     fhew
    0.50
     katze
    0.49
     Photocase
    0.48
     Wikispecies
    0.48
    AddTagHelper
    0.48
    Activations Density 0.001%

    No Known Activations