© 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. 2123
    Prev
    Next
    INDEX
    Explanations

    Technical/Code

    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
     فريبيس
    -0.74
    AxisAlignment
    -0.72
    MemoryWarning
    -0.70
     NSCoder
    -0.69
    SuccessListener
    -0.61
     TextAppearance
    -0.59
    RenderAtEndOf
    -0.57
     AssemblyVersion
    -0.56
    makeText
    -0.56
    таратура
    -0.55
    POSITIVE LOGITS
    um
    0.55
     plainte
    0.52
    AntiForgeryToken
    0.48
     oprot
    0.48
    ite
    0.48
    tagext
    0.45
    پیوند
    0.44
     nip
    0.44
     nit
    0.43
     ple
    0.43
    Activations Density 0.004%

    No Known Activations