© 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. 17349
    Prev
    Next
    INDEX
    Explanations

    specific terms related to data structures and system performance

    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
     purpoſe
    -0.82
     ſtate
    -0.81
     houſe
    -0.81
     reaſon
    -0.76
     uſe
    -0.73
     متعلقه
    -0.71
     Reſ
    -0.71
     ſtand
    -0.70
     automatiques
    -0.69
     ſmall
    -0.68
    POSITIVE LOGITS
     @"/
    0.59
     виправивши
    0.46
     MainAxisSize
    0.46
    ])));
    0.45
    MockMvc
    0.44
     …
    0.43
    abestanden
    0.42
     dal
    0.41
    اص
    0.41
     thiệu
    0.41
    Activations Density 0.597%

    No Known Activations