© 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. 31880
    Prev
    Next
    INDEX
    Explanations

    specialized terminology related to chemical processes and transformations

    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
    getWriter
    -0.88
    expandindo
    -0.83
    windowFixed
    -0.81
     hidrá
    -0.81
    ^(@)
    -0.79
     abbraccio
    -0.75
    resaid
    -0.74
    ---+
    -0.74
     Forumite
    -0.74
    ANNES
    -0.74
    POSITIVE LOGITS
     Des
    0.62
    Decrypt
    0.61
    (_
    0.60
     deth
    0.59
     Unmarshal
    0.59
    decode
    0.57
     _
    0.56
    Des
    0.56
     (_
    0.55
     decoding
    0.55
    Activations Density 0.059%

    No Known Activations