© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4474
    Prev
    Next
    INDEX
    Explanations

    colon punctuation

    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
     Monfieur
    -0.55
     raiſ
    -0.54
     uſed
    -0.54
     fince
    -0.53
     juſ
    -0.51
    Suisse
    -0.50
    GraphicsUnit
    -0.49
     Diſ
    -0.48
    ftagPool
    -0.47
     purpoſe
    -0.46
    POSITIVE LOGITS
    Diweddarwch
    0.70
    Portale
    0.68
     EconPapers
    0.67
     незавершена
    0.66
     otomatig
    0.62
    rawDesc
    0.61
     հղումներ
    0.58
    writeField
    0.58
    Хьажоргаш
    0.58
    scriptcase
    0.57
    Activations Density 0.005%

    No Known Activations