© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 461
    Prev
    Next
    INDEX
    Explanations

    Roberts

    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
     Roberts
    -1.21
    Roberts
    -1.00
     ROBERTS
    -0.99
     AssemblyCompany
    -0.62
     Goddard
    -0.58
     onCancelled
    -0.52
    Попис
    -0.48
     Umständen
    -0.47
     guardia
    -0.45
     знаний
    -0.45
    POSITIVE LOGITS
     UserDao
    0.60
    hpp
    0.58
     Spaces
    0.58
     Reverso
    0.56
    haw
    0.55
    łaszcza
    0.54
     CanadaChoose
    0.54
    livejournal
    0.53
     noDo
    0.53
    hes
    0.52
    Activations Density 0.195%

    No Known Activations