© 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. 4558
    Prev
    Next
    INDEX
    Explanations

    star

    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
     المعيارى
    -0.59
     TextFormField
    -0.57
     travailleurs
    -0.56
     متعلقه
    -0.55
     mauvaises
    -0.55
     cœurs
    -0.52
     Taktlose
    -0.52
    Viited
    -0.52
     '\\;'
    -0.50
    chyma
    -0.48
    POSITIVE LOGITS
     समीक्षाओं
    0.75
    IndentedString
    0.63
     requirements
    0.58
     value
    0.54
     features
    0.54
     Paul
    0.54
     Ngày
    0.53
     selected
    0.53
     restaurants
    0.53
     this
    0.50
    Activations Density 0.048%

    No Known Activations