© 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. 0-CLT-HP
    7. 44129
    Prev
    Next
    INDEX
    Explanations

    decomposition

    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
     disambiguazione
    -0.99
    ThroughAttribute
    -0.97
    BufferException
    -0.93
    клопе
    -0.91
     ujednoznacz
    -0.91
     للمعارف
    -0.88
     Roskov
    -0.88
     AssemblyTitle
    -0.87
     FetchType
    -0.86
     autorytatywna
    -0.85
    POSITIVE LOGITS
    e
    0.74
    ی
    0.67
    y
    0.59
     center
    0.57
    ally
    0.56
     model
    0.50
    i
    0.48
    er
    0.47
     process
    0.46
    서
    0.46
    Activations Density 0.082%

    No Known Activations