© 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. 22-RES-MATRYOSHKA-DC
    7. 439
    Prev
    Next
    INDEX
    Explanations

    words related to online shopping orders and shipping

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    LookAnd
    -0.91
     Мексичка
    -0.88
     Савезне
    -0.87
     فريبيس
    -0.84
    发表于
    -0.83
    HideFlags
    -0.78
    ########.
    -0.77
    contentLoaded
    -0.76
     JpaRepository
    -0.73
    bootstrapcdn
    -0.71
    POSITIVE LOGITS
     email
    1.08
     contact
    0.98
     please
    0.96
     FREE
    0.93
     emailed
    0.90
     your
    0.90
     Please
    0.86
     Contact
    0.85
     signup
    0.82
    contact
    0.82
    Activations Density 2.845%

    No Known Activations