© 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. 95013
    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
    MessageTagHelper
    -0.64
    ьаж
    -0.60
    CloseOperation
    -0.59
    istoitu
    -0.57
    yttö
    -0.54
     الدولى
    -0.52
    щами
    -0.52
    {}",
    -0.51
     '.')
    -0.51
    reton
    -0.50
    POSITIVE LOGITS
    utilisons
    0.63
     <<<<<<<<<<<<<<
    0.57
    
    0.57
    NameInMap
    0.55
     acadé
    0.53
    enseignement
    0.50
    NgModule
    0.50
     Codable
    0.50
     linkovi
    0.49
     AMT
    0.49
    Activations Density 0.000%

    No Known Activations