© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 210
    Prev
    Next
    INDEX
    Explanations

    technical and procedural language related to processes and actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    -
    -0.86
     
    -0.76
     up
    -0.69
    <h2>
    -0.69
    /
    -0.69
    t
    -0.68
    1
    -0.66
    \
    -0.66
    ,
    -0.65
    H
    -0.65
    POSITIVE LOGITS
     myſelf
    1.36
    )");
    
    1.25
     Efq
    1.13
     themſelves
    1.13
    )"),
    1.11
     ſeveral
    1.10
     itſelf
    1.09
    )";
    
    1.08
     Forumite
    1.07
     $_"
    1.07
    Activations Density 6.587%

    No Known Activations