© 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. 22-RES-MATRYOSHKA-DC
    7. 2478
    Prev
    Next
    INDEX
    Explanations

    discourse markers and logical connectives

    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
    Unfortunately
    -0.56
     Unfortunately
    -0.55
    Leider
    -0.54
     Leider
    -0.54
     особо
    -0.54
    yyj
    -0.53
    iestety
    -0.52
    可惜
    -0.51
    Počet
    -0.50
    dolu
    -0.49
    POSITIVE LOGITS
     instead
    3.13
     Instead
    3.00
    Instead
    2.95
    instead
    2.84
     rather
    2.67
     Rather
    2.63
    Rather
    2.55
     vielmehr
    2.53
    rather
    2.42
     plutôt
    2.17
    Activations Density 0.700%

    No Known Activations