© 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. 650
    Prev
    Next
    INDEX
    Explanations

    text from legal documents and statutes

    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
     BorderRadius
    -0.60
     conducted
    -0.58
     Conducted
    -0.56
     gewonnen
    -0.55
     performed
    -0.49
     atlik
    -0.48
     valgt
    -0.48
     EdgeInsets
    -0.47
    íteni
    -0.47
    kable
    -0.47
    POSITIVE LOGITS
     specifies
    1.08
     specify
    1.05
     stip
    1.00
     stipul
    0.98
     specifying
    0.91
     expressly
    0.87
     explicitly
    0.87
     Specify
    0.86
    specify
    0.81
     forbid
    0.80
    Activations Density 1.141%

    No Known Activations