© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 29915
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the "Deep State" and related political dynamics

    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
     offering
    -0.54
     menarik
    -0.53
     betekenis
    -0.52
    AsUp
    -0.52
    ntö
    -0.52
    Билгалдахарш
    -0.49
    庁
    -0.49
     significativos
    -0.49
     σύ
    -0.48
     ofrecen
    -0.48
    POSITIVE LOGITS
    TemporalType
    0.65
     propOrder
    0.64
    soever
    0.60
    resented
    0.58
    noons
    0.57
    ollectionView
    0.55
     /\.
    0.54
    \{\\
    0.54
    /******/
    0.54
     acknowled
    0.53
    Activations Density 0.191%

    No Known Activations