© 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. 20870
    Prev
    Next
    INDEX
    Explanations

    phrases or terms indicating quotations or references

    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
     myſelf
    -1.31
     raiſ
    -1.15
     himſelf
    -1.14
     Efq
    -1.13
    ſelf
    -1.13
     photolibrary
    -1.13
     houſe
    -1.13
     itſelf
    -1.10
     purpoſe
    -1.08
     uſed
    -1.08
    POSITIVE LOGITS
    <eos>
    0.68
     
    0.59
    AddHtmlAttribute
    0.57
     *
    0.57
     (
    0.56
     '
    0.53
    .
    0.52
     the
    0.51
    ↵↵
    0.50
     "
    0.50
    Activations Density 0.007%

    No Known Activations