© 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. 95237
    Prev
    Next
    INDEX
    Explanations

    professions

    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
     reviewed
    -0.46
     règlement
    -0.45
     Вікі
    -0.45
    류
    -0.44
    avir
    -0.43
    chafts
    -0.43
     المعيارى
    -0.42
    ype
    -0.42
     redenen
    -0.42
    estinal
    -0.42
    POSITIVE LOGITS
     AssemblyCompany
    0.73
     AssemblyTitle
    0.60
    Atsauces
    0.60
    ForRow
    0.59
    Veteran
    0.58
     veteran
    0.58
    ricorn
    0.57
     ujednoznacz
    0.57
     salesperson
    0.55
     investor
    0.54
    Activations Density 0.007%

    No Known Activations