© 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. 18574
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, specifically comments and delimiters

    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
    Occurred
    -0.49
     يتيمه
    -0.47
    pení
    -0.47
    ücher
    -0.46
     المعيارى
    -0.45
    herin
    -0.44
    czaj
    -0.44
    rinth
    -0.43
     Nare
    -0.43
    пля
    -0.43
    POSITIVE LOGITS
    AndroidJUnit
    0.78
    SpringBoot
    0.72
    TestingModule
    0.71
    Portale
    0.69
    ImageContext
    0.65
    ValueStyle
    0.63
    ContentAlignment
    0.63
    keyColumn
    0.63
    adamia
    0.62
    LookAnd
    0.61
    Activations Density 0.002%

    No Known Activations