© 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. 9630
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biological markers and regulatory proteins

    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
     heapq
    -0.62
     useParams
    -0.56
    encodeWith
    -0.54
    rawdę
    -0.54
     createSlice
    -0.54
     상세
    -0.53
     delegate
    -0.52
    ResumeLayout
    -0.52
    icmp
    -0.51
    unhofer
    -0.51
    POSITIVE LOGITS
    ToBounds
    0.56
    antaranya
    0.53
     Fore
    0.53
    mybatisplus
    0.52
    hias
    0.52
    жалуйста
    0.52
    SerializedName
    0.49
    ğına
    0.49
    IsContent
    0.47
     تد
    0.47
    Activations Density 0.057%

    No Known Activations