© 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. 97551
    Prev
    Next
    INDEX
    Explanations

    caught

    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
     caught
    -0.72
     Hold
    -0.57
     holds
    -0.56
     Holding
    -0.52
     catch
    -0.52
     hold
    -0.49
    Hold
    -0.48
    Holding
    -0.48
     مشين
    -0.48
     accesso
    -0.48
    POSITIVE LOGITS
    MockBean
    0.76
     سكانية
    0.74
    хьтан
    0.69
    Diweddarwch
    0.65
    RegressionTest
    0.65
    ografija
    0.63
     defaultstate
    0.61
    piac
    0.60
     дописавши
    0.60
    |}{$
    0.60
    Activations Density 0.095%

    No Known Activations