© 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. 8551
    Prev
    Next
    INDEX
    Explanations

    references to corporate structures and ownership relationships

    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
    tagHelperRunner
    -0.68
     متعلقه
    -0.63
    ]._
    -0.58
    rungsseite
    -0.56
    helin
    -0.55
    Дина
    -0.54
     remote
    -0.54
    vario
    -0.53
     noten
    -0.52
    さまでした
    -0.52
    POSITIVE LOGITS
    WebElementEntity
    0.60
    elemField
    0.59
     Chriftian
    0.57
     Cæsar
    0.57
    HttpPut
    0.57
     Majefty
    0.56
     feveral
    0.55
     Jefus
    0.55
    شهاد
    0.55
     ſeveral
    0.55
    Activations Density 0.035%

    No Known Activations