© 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. 2504
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially periods, commas, and exclamation points, often near discourse markers like "but" or "then".

    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
    pierw
    -0.64
     cioè
    -0.62
    
    -0.57
     solcher
    -0.57
     estekak
    -0.56
    MemoryWarning
    -0.55
    jsonwebtoken
    -0.54
     beteiligt
    -0.53
    docx
    -0.52
    是这样
    -0.51
    POSITIVE LOGITS
    Overall
    1.14
     Overall
    1.11
     overall
    1.05
    overall
    0.93
     aside
    0.89
     Speaking
    0.84
    OVERALL
    0.80
     Granted
    0.78
    Speaking
    0.78
     Lastly
    0.77
    Activations Density 0.303%

    No Known Activations