© 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. 30358
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and their relationships to equations or mathematical expressions

    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
    TestingModule
    -0.62
     Harp
    -0.57
     about
    -0.56
    caches
    -0.56
    </code>
    -0.55
     Bourgoin
    -0.55
     Wer
    -0.53
     Chwiliwch
    -0.53
    Controllo
    -0.53
    发表于
    -0.52
    POSITIVE LOGITS
     getRule
    0.78
    GenerationType
    0.78
    lotl
    0.77
    PickerController
    0.72
    trex
    0.71
    ximity
    0.71
    jandra
    0.70
    GYPT
    0.70
     Loth
    0.70
    ViewFeatures
    0.70
    Activations Density 0.070%

    No Known Activations