© 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. 9516
    Prev
    Next
    INDEX
    Explanations

    references to conserved genetic sequences or regions

    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
     tids
    -0.52
     rối
    -0.52
    γη
    -0.52
    Multipart
    -0.46
     zda
    -0.46
     صوتيه
    -0.45
     stazione
    -0.45
     raisons
    -0.44
    marvin
    -0.44
     gouttes
    -0.44
    POSITIVE LOGITS
    sidemargin
    1.06
     conserved
    1.02
    __(/*!
    0.88
    GraphicsUnit
    0.85
     conserving
    0.84
     conservation
    0.82
     CONSERVATION
    0.81
     conserve
    0.80
     conserva
    0.80
     jLabel
    0.78
    Activations Density 0.002%

    No Known Activations