© 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. 18-RES-MATRYOSHKA-DC
    7. 939
    Prev
    Next
    INDEX
    Explanations

    words/phrases in emails like "comments", "manuscript", "text has been changed" and "constructive"

    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.18.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.18.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
    preventDefault
    -0.47
    šky
    -0.40
     /^[
    -0.39
     melindungi
    -0.38
     mencegah
    -0.38
    lichkeit
    -0.38
    osse
    -0.38
     berakhir
    -0.38
    stopPropagation
    -0.37
    Fails
    -0.37
    POSITIVE LOGITS
     changes
    2.28
     change
    2.14
     changed
    2.05
     Changes
    2.02
    changes
    1.98
    Changes
    1.91
    change
    1.83
     CHANGES
    1.81
    changed
    1.80
     Changed
    1.80
    Activations Density 3.178%

    No Known Activations