© 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. 97766
    Prev
    Next
    INDEX
    Explanations

    each

    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
     each
    -1.07
    Each
    -0.92
    Lord
    -0.84
     Each
    -0.83
    each
    -0.82
     fiecare
    -0.81
     Lord
    -0.79
     ciascuno
    -0.73
     ciasc
    -0.72
     leaſt
    -0.71
    POSITIVE LOGITS
     time
    0.56
     &
    0.53
    حياته
    0.48
    time
    0.48
     persons
    0.47
     of
    0.47
    endpush
    0.47
     CURIAM
    0.46
     שוליים
    0.45
     and
    0.44
    Activations Density 0.035%

    No Known Activations