© 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. 25874
    Prev
    Next
    INDEX
    Explanations

    references to figures and diagrams in the text

    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
     vazio
    -0.54
     sozinho
    -0.49
     Dänemark
    -0.48
     vold
    -0.48
     absolu
    -0.47
    Kết
    -0.47
     Russie
    -0.47
    kari
    -0.47
    halla
    -0.47
    igrette
    -0.47
    POSITIVE LOGITS
    #+#
    1.03
    LookAnd
    1.01
     оригіналу
    0.93
     snippetHide
    0.92
    ($__
    0.90
    IsMutable
    0.88
     Signalez
    0.85
    AndEndTag
    0.85
     unknownFields
    0.82
    MigrationBuilder
    0.80
    Activations Density 0.010%

    No Known Activations