© 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. 20984
    Prev
    Next
    INDEX
    Explanations

    numerical data and references related to statistical analyses or measurements

    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
    EDEFAULT
    -0.71
     Registers
    -0.67
     BoxFit
    -0.67
     houſe
    -0.67
     Theſe
    -0.66
     HasFactory
    -0.66
     purpoſe
    -0.66
     pleaſure
    -0.66
     greateſt
    -0.66
     Houſe
    -0.64
    POSITIVE LOGITS
    DoubleQuotes
    0.60
     A
    0.49
     Bal
    0.49
     No
    0.48
     Ex
    0.48
     |
    0.47
    খন
    0.47
     Multi
    0.45
     Mat
    0.45
     Our
    0.45
    Activations Density 0.168%

    No Known Activations