© 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. 24547
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences in numerical 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
    Not in Any Lists

    No Comments

    Negative Logits
     soprav
    -0.64
     chré
    -0.62
    +#+#
    -0.60
     épar
    -0.59
    LEEP
    -0.57
    amling
    -0.57
    WillAppear
    -0.56
     fib
    -0.55
     oeufs
    -0.55
     chrétiens
    -0.55
    POSITIVE LOGITS
      
    0.79
    TypedDataSet
    0.77
    Datuak
    0.69
    ssohn
    0.69
    ArgsConstructor
    0.67
     Eisenberg
    0.63
     
    0.63
    )‏
    0.62
     Regard
    0.62
     Cullen
    0.61
    Activations Density 0.003%

    No Known Activations