© 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. 97684
    Prev
    Next
    INDEX
    Explanations

    various kinds of documents

    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
     geçen
    -0.60
    ScopeManager
    -0.59
    ībā
    -0.59
    bní
    -0.54
    EndContext
    -0.53
    colnshire
    -0.52
     становника
    -0.52
     blancas
    -0.51
     IEnumerator
    -0.51
    
    -0.51
    POSITIVE LOGITS
    ########.
    0.95
     ostavi
    0.78
     ProtoMessage
    0.68
    hideLoading
    0.60
     Seeder
    0.58
    isko
    0.57
    elemField
    0.54
     Besøkt
    0.54
    ensement
    0.54
     transfieras
    0.54
    Activations Density 1.844%

    No Known Activations