© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    main

    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
    الإنجليزية
    -0.59
     "
    -0.57
     “
    -0.54
     المعيارى
    -0.53
     صوتيه
    -0.44
    ↵↵
    -0.44
    USES
    -0.44
     Folge
    -0.43
     ``
    -0.43
     douce
    -0.43
    POSITIVE LOGITS
    <bos>
    1.55
    TagMode
    0.69
     referenties
    0.54
     sighting
    0.54
    uxxxx
    0.53
    thebibliography
    0.52
    Хьажоргаш
    0.52
     sightings
    0.52
     Мексичка
    0.51
     кӀ
    0.51
    Activations Density 0.002%

    No Known Activations