© 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. 38881
    Prev
    Next
    INDEX
    Explanations

    Occupations ending in "-ers"

    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
     réguli
    -0.78
     normaux
    -0.67
     supérieurs
    -0.67
     abstrait
    -0.66
     scolaires
    -0.65
     financières
    -0.65
     complètes
    -0.65
     optique
    -0.62
     traditionnels
    -0.62
     isComment
    -0.61
    POSITIVE LOGITS
     تضيفلها
    0.81
    SourceChecksum
    0.70
    /**
    0.66
    ContentAsync
    0.63
    +',
    0.60
    principalTable
    0.59
     مواليد
    0.59
    webElementGuid
    0.59
    клопе
    0.58
    исленность
    0.56
    Activations Density 0.098%

    No Known Activations