© 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. 97586
    Prev
    Next
    INDEX
    Explanations

    legal and business matters

    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
    GraphicsUnit
    -0.82
     nakalista
    -0.81
     Exacts
    -0.79
    complexContent
    -0.78
     Мексичка
    -0.78
    talk
    -0.76
    ՚
    -0.75
     becauſe
    -0.73
     Efq
    -0.72
     FetchType
    -0.72
    POSITIVE LOGITS
     pro
    0.52
     go
    0.49
     rest
    0.47
     red
    0.44
     re
    0.44
     raised
    0.44
     dead
    0.43
     goes
    0.43
     pulled
    0.43
     
    0.43
    Activations Density 1.468%

    No Known Activations