© 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. 38849
    Prev
    Next
    INDEX
    Explanations

    Petersburg

    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
     Petersburg
    -1.45
    bootstrapcdn
    -0.81
     getItemCount
    -0.78
    tagHelperRunner
    -0.77
    WebVitals
    -0.76
     paral
    -0.75
     vivi
    -0.68
     Paral
    -0.67
     DRS
    -0.66
     Thales
    -0.65
    POSITIVE LOGITS
    Geplaatst
    0.56
     autorytatywna
    0.52
     rayos
    0.48
     camiones
    0.48
    <eos>
    0.45
     sayap
    0.45
    vol
    0.44
     disponibilità
    0.44
     cuartos
    0.43
     hospod
    0.43
    Activations Density 0.194%

    No Known Activations