© 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. 14850
    Prev
    Next
    INDEX
    Explanations

    scientific references and related citations

    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
     hal
    -0.42
    sec
    -0.41
    মান
    -0.41
    к
    -0.40
     "
    -0.38
    Comment
    -0.38
     Hal
    -0.37
    sette
    -0.37
    ող
    -0.36
    nought
    -0.36
    POSITIVE LOGITS
     lenker
    0.90
    Hentet
    0.84
    protoimpl
    0.81
    IntoConstraints
    0.80
    RectangleBorder
    0.79
    WebServlet
    0.79
    CloseOperation
    0.75
    providedIn
    0.73
    الحياه
    0.73
    — 
    0.73
    Activations Density 0.016%

    No Known Activations