© 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. 1-CLT-HP
    7. 12141
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     незавершена
    -0.71
     مرئيه
    -0.68
    CloseOperation
    -0.68
     للاسماء
    -0.65
    NameInMap
    -0.62
    ximity
    -0.61
     consultato
    -0.60
    GEBURTSDATUM
    -0.60
     okuyayım
    -0.59
    InitStruct
    -0.57
    POSITIVE LOGITS
    Recur
    0.54
     errore
    0.47
    reload
    0.47
    traces
    0.47
    Reload
    0.46
     efficiency
    0.45
     Trace
    0.45
    rippa
    0.45
     regrets
    0.45
     ulei
    0.45
    Activations Density 0.024%

    No Known Activations