© 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. 1226
    Prev
    Next
    INDEX
    Explanations

    strikes

    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
     AssemblyCulture
    -0.87
     étoient
    -0.82
     estekak
    -0.82
     שוליים
    -0.78
     مرئيه
    -0.77
    قایناق‌لار
    -0.74
     avoient
    -0.72
     myſelf
    -0.72
     houſe
    -0.70
     Jefus
    -0.69
    POSITIVE LOGITS
     “
    0.55
    isse
    0.50
     gre
    0.44
     bas
    0.44
     ‘
    0.43
    (
    0.41
     maio
    0.41
     gu
    0.41
    tainen
    0.41
     bul
    0.41
    Activations Density 0.000%

    No Known Activations