© 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. 12-RES-MATRYOSHKA-DC
    7. 5021
    Prev
    Next
    INDEX
    Explanations

    legal references to statutes or provisions

    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
     للمعارف
    -0.92
    IActionResult
    -0.92
     Jule
    -0.85
     KeyEvent
    -0.84
     ModelExpression
    -0.84
     AspNetCore
    -0.81
     Bianchi
    -0.80
    ukah
    -0.78
     Chartres
    -0.77
     MotionEvent
    -0.77
    POSITIVE LOGITS
     Provision
    1.47
     Provisions
    1.45
    Provision
    1.43
     provision
    1.38
     provisions
    1.38
    provision
    1.32
     PROVISIONS
    1.30
     provisioning
    0.96
     provis
    0.81
     prov
    0.69
    Activations Density 0.015%

    No Known Activations