© 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. 25961
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and components, particularly in a Java or JavaScript context

    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
    \{\\
    -0.53
     المعيارى
    -0.52
    ndig
    -0.48
    mediate
    -0.48
     concussion
    -0.48
     Tumble
    -0.47
    cussed
    -0.46
    toir
    -0.46
    cussions
    -0.45
    …).
    -0.45
    POSITIVE LOGITS
    SpringBootTest
    0.89
    UnitTesting
    0.81
     verrez
    0.68
    tagHelperRunner
    0.67
    SourceChecksum
    0.65
    expandindo
    0.63
    verwijspagina
    0.63
    ExtendWith
    0.63
    ControllerTest
    0.61
    AppCompat
    0.60
    Activations Density 0.031%

    No Known Activations