© 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. 9450
    Prev
    Next
    INDEX
    Explanations

    phrases that denote references 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
    Negative Logits
    globalData
    -0.68
    stens
    -0.64
    maximal
    -0.63
    댑
    -0.63
    asier
    -0.61
    SOUNDBITE
    -0.61
     Hessen
    -0.61
    ITEN
    -0.61
    OrEqual
    -0.61
     rezept
    -0.60
    POSITIVE LOGITS
     useRef
    0.96
     '\\;'
    0.90
     allude
    0.72
     referred
    0.72
    UrlResolution
    0.71
     REFER
    0.70
    ="@+
    0.69
     referring
    0.69
    Хьажоргаш
    0.69
     refer
    0.68
    Activations Density 0.016%

    No Known Activations