© 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. 4-CLT-HP
    7. 3375
    Prev
    Next
    INDEX
    Explanations

    government/politics

    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
     HasFactory
    -0.57
     Streptococcus
    -0.55
    }))
    -0.54
    QMetaType
    -0.52
     sociétés
    -0.52
     âmes
    -0.51
     rallado
    -0.51
    RegistryLite
    -0.51
     <=",
    -0.50
    systems
    -0.49
    POSITIVE LOGITS
     Obama
    0.66
     Barack
    0.63
    inghouse
    0.63
    Obama
    0.60
     AssemblyCompany
    0.60
     AssemblyVersion
    0.54
     elect
    0.53
    Prez
    0.53
     Presidential
    0.53
     Election
    0.50
    Activations Density 0.028%

    No Known Activations