© 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. 1117
    Prev
    Next
    INDEX
    Explanations

    inheritance

    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
     GenerationType
    -0.62
    forChild
    -0.60
     CURIAM
    -0.59
     kasarigan
    -0.58
    StoryboardSegue
    -0.56
    weep
    -0.54
     germinate
    -0.54
    RectangleBorder
    -0.54
    ösungen
    -0.52
    Bibliograf
    -0.51
    POSITIVE LOGITS
     gyhoeddwyd
    0.53
    Демографія
    0.52
     extérieurs
    0.50
    ībā
    0.49
     légale
    0.48
     histórico
    0.48
     juiste
    0.46
     mundiales
    0.46
    kennung
    0.46
     físicas
    0.46
    Activations Density 0.001%

    No Known Activations