© 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. 26213
    Prev
    Next
    INDEX
    Explanations

    mathematical or structural patterns in the text

    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
    PerformLayout
    -0.61
    ("$.
    -0.54
    DeleteBehavior
    -0.51
    IBOutlet
    -0.51
    NewGuid
    -0.51
    ','.
    -0.50
    "/>
    -0.50
     grà
    -0.50
    myapplication
    -0.49
    IVEREF
    -0.49
    POSITIVE LOGITS
    Rhestr
    0.61
    tagext
    0.58
     esternos
    0.57
    tioner
    0.56
     fields
    0.56
    wnież
    0.55
     Aps
    0.55
    Fields
    0.55
     isKindOfClass
    0.54
     pinulongan
    0.53
    Activations Density 0.004%

    No Known Activations