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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4513
    Prev
    Next
    INDEX
    Explanations

    references to specific purposes or intentions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انتهای
    -1.02
     itſelf
    -0.96
    kháu
    -0.96
    WaitGroup
    -0.94
    WithIOException
    -0.92
     Richelieu
    -0.91
    AndroidJUnit
    -0.90
    ArrowToggle
    -0.89
     AspNetCore
    -0.88
     Swarovski
    -0.88
    POSITIVE LOGITS
     Purpose
    1.13
     purposes
    1.08
    Purpose
    1.05
    PURPOSE
    1.02
     Purposes
    1.01
     PURPOSE
    0.94
    purpose
    0.88
     purpose
    0.83
    purposes
    0.82
    ể
    0.77
    Activations Density 0.020%

    No Known Activations