© 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. 23214
    Prev
    Next
    INDEX
    Explanations

    practical tips and recommendations for improvement

    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
     religieuses
    -0.60
     pleaſure
    -0.59
    readFileSync
    -0.58
    脚注の使い方
    -0.56
    ſelf
    -0.54
     Luar
    -0.54
    IUrlHelper
    -0.54
    argout
    -0.53
    complexContent
    -0.53
     kife
    -0.52
    POSITIVE LOGITS
     advice
    0.89
     tips
    0.83
     Advice
    0.80
     advisable
    0.80
     advised
    0.79
     ADVICE
    0.79
    Advice
    0.76
     consejos
    0.76
     Tips
    0.75
     recommended
    0.75
    Activations Density 0.418%

    No Known Activations