© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4757
    Prev
    Next
    INDEX
    Explanations

    ́

    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
    Personendaten
    -0.68
    DeleteBehavior
    -0.60
     للمعارف
    -0.58
    RenderAtEndOf
    -0.54
    XtraGrid
    -0.51
    oredCriteria
    -0.51
    StoryboardSegue
    -0.50
    XmlAccessType
    -0.50
    ValueStyle
    -0.50
    ItemSelected
    -0.49
    POSITIVE LOGITS
     ad
    0.56
     nd
    0.54
    }`}>
    0.53
     n
    0.52
     –
    0.52
     np
    0.52
     p
    0.51
     le
    0.51
     State
    0.51
     nn
    0.50
    Activations Density 0.001%

    No Known Activations