© 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. 31999
    Prev
    Next
    INDEX
    Explanations

    sections of content that indicate significant results or conclusions in research

    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
    URLException
    -0.69
    +#+
    -0.63
     calendriers
    -0.63
     igenom
    -0.56
     متعلقه
    -0.56
    دانشنامهٔ
    -0.55
    gdala
    -0.50
    nachron
    -0.50
    didSet
    -0.50
     sûr
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.72
    multicolumn
    0.57
     trữ
    0.56
    DrawerToggle
    0.55
    pielen
    0.54
     haunt
    0.51
     Saviour
    0.49
    Ati
    0.49
    onomía
    0.49
     pauper
    0.49
    Activations Density 0.009%

    No Known Activations