© 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. 742
    Prev
    Next
    INDEX
    Explanations

    terms related to search engine optimization and pay-per-click advertising

    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
    Према
    -0.60
     Civilian
    -0.60
     civilian
    -0.52
     <>",
    -0.51
     disassembly
    -0.50
     cutaneous
    -0.50
    ̀n
    -0.48
    zieher
    -0.48
     Audiodateien
    -0.48
    ectoria
    -0.48
    POSITIVE LOGITS
     SEO
    1.13
    SEO
    1.01
     traffic
    1.00
     marketing
    1.00
     seo
    0.90
     marketers
    0.89
     visitors
    0.88
     Marketing
    0.84
    marketing
    0.83
     keyword
    0.82
    Activations Density 0.939%

    No Known Activations