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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21741
    Prev
    Next
    INDEX
    Explanations

    references to specific studies or citations

    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
     "
    -0.60
     of
    -0.59
     (
    -0.56
    ,
    -0.55
    H
    -0.50
     
    -0.49
    es
    -0.48
    '
    -0.48
    id
    -0.47
     sub
    -0.47
    POSITIVE LOGITS
    __*/
    1.08
     bezeichneter
    0.95
     الحره
    0.94
    ViewImports
    0.94
    posedge
    0.94
    adpleegd
    0.94
    StoryboardSegue
    0.94
    ."));
    0.92
    URLException
    0.92
    __":
    0.92
    Activations Density 0.006%

    No Known Activations