© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    definitions

    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
     being
    -0.59
    being
    -0.56
    ']")
    -0.55
    runge
    -0.49
    '})
    -0.49
    Being
    -0.48
     Kreise
    -0.48
     needing
    -0.48
    Datuak
    -0.47
    ritch
    -0.47
    POSITIVE LOGITS
    ,
    0.89
     “
    0.82
     "
    0.69
    “
    0.66
    ,“
    0.64
    、「
    0.60
    ,”
    0.58
    ，「
    0.57
    ，“
    0.57
     «
    0.57
    Activations Density 0.003%

    No Known Activations