© 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. 17022
    Prev
    Next
    INDEX
    Explanations

    numerical and legal citation 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
    Negative Logits
    rest
    -0.63
     rest
    -0.62
     colspan
    -0.59
    </em>
    -0.56
    <strong>
    -0.55
    <b>
    -0.52
    </h2>
    -0.51
     re
    -0.51
     ride
    -0.51
    </h3>
    -0.50
    POSITIVE LOGITS
     Efq
    0.88
     myſelf
    0.79
     Monfieur
    0.78
     becauſe
    0.77
     Jefus
    0.76
     chofe
    0.74
     Meksiku
    0.73
    <?
    0.73
     raiſ
    0.73
     Chriftian
    0.73
    Activations Density 0.041%

    No Known Activations