© 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. 1957
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     énergé
    -0.49
     avvic
    -0.47
     fondament
    -0.45
    Giá
    -0.45
     sådan
    -0.43
     abbin
    -0.43
     automatique
    -0.42
     aján
    -0.40
     automatiques
    -0.39
    енча
    -0.38
    POSITIVE LOGITS
    
    0.92
    Hochspringen
    0.85
    ChildScrollView
    0.81
     مرئيه
    0.79
     nahilalakip
    0.79
    Попис
    0.79
     snippetHide
    0.78
    IUrlHelper
    0.76
    DispatchToProps
    0.75
    #+#
    0.75
    Activations Density 0.000%

    No Known Activations