© 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. 5-CLT-HP
    7. 96081
    Prev
    Next
    INDEX
    Explanations

    Acronyms and numbers

    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
     CNRS
    -0.88
     wireType
    -0.60
     препратки
    -0.58
    atella
    -0.55
     محفوظة
    -0.54
    xtures
    -0.53
    asantry
    -0.50
    ectady
    -0.50
    ština
    -0.49
    acide
    -0.49
    POSITIVE LOGITS
    مصادر
    0.67
    Personendaten
    0.55
     nemlig
    0.52
    U
    0.52
    LU
    0.51
     colpa
    0.50
     hvem
    0.50
     Electra
    0.50
    complexContent
    0.49
     superiori
    0.49
    Activations Density 0.004%

    No Known Activations