© 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. 2683
    Prev
    Next
    INDEX
    Explanations

    specific legal or regulatory references, particularly related to health and service entities

    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
     GenerationType
    -0.68
     Winaray
    -0.67
    tagHelperRunner
    -0.64
     ddelweddau
    -0.58
    ériale
    -0.58
    ValueStyle
    -0.58
     @"/
    -0.58
    )':
    -0.58
    ousands
    -0.57
     Marcell
    -0.57
    POSITIVE LOGITS
    GEBURTSDATUM
    0.54
     AttributeSet
    0.50
    IBOutlet
    0.49
    spaceBetween
    0.49
     Référence
    0.49
    OrBuilder
    0.48
     noqa
    0.48
    Axel
    0.47
    ecma
    0.46
    odon
    0.46
    Activations Density 0.039%

    No Known Activations