© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9389
    Prev
    Next
    INDEX
    Explanations

    tables summarizing data

    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
    Negative Logits
     يتيمه
    -1.04
     disambiguazione
    -1.04
    IndentedString
    -0.96
    sidemargin
    -0.93
     Signalez
    -0.92
    DeleteMapping
    -0.89
    SceneManagement
    -0.87
     كومونز
    -0.85
     IndexPath
    -0.84
     للمعارف
    -0.82
    POSITIVE LOGITS
    ↵↵
    0.55
    not
    0.48
     condensed
    0.46
    rod
    0.44
    翼
    0.43
     
    0.43
    Invocation
    0.43
    UpDown
    0.42
     انداز
    0.42
     natural
    0.42
    Activations Density 0.006%

    No Known Activations