© 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. 38829
    Prev
    Next
    INDEX
    Explanations

    seen

    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
     seen
    -1.82
    seen
    -1.36
     Seen
    -1.31
    Seen
    -1.22
     SEEN
    -1.13
     gezien
    -1.02
     visto
    -0.94
     vistos
    -0.91
     feen
    -0.91
     gesehen
    -0.86
    POSITIVE LOGITS
     the
    0.70
     "
    0.56
     T
    0.52
    öl
    0.51
    \\
    0.50
     '
    0.49
     my
    0.48
    SpringBootTest
    0.48
    /
    0.48
    0.48
    Activations Density 0.120%
    No Known Activations