© 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. 2131
    Prev
    Next
    INDEX
    Explanations

    actually

    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
    principalColumn
    -0.77
     mourut
    -0.71
     médicale
    -0.65
     financière
    -0.65
    ServletException
    -0.63
    ///</
    -0.63
     chrétienne
    -0.62
     ogen
    -0.61
    MemoryWarning
    -0.60
     citoy
    -0.60
    POSITIVE LOGITS
     go
    0.71
     sit
    0.67
     perform
    0.63
     see
    0.61
     implement
    0.59
     engage
    0.57
     deal
    0.57
     configure
    0.57
     undertake
    0.56
     start
    0.55
    Activations Density 0.002%

    No Known Activations