© 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. 8761
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to function definitions and constructor calls in programming

    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
     disambiguazione
    -0.77
    writeFieldEnd
    -0.69
    GEBURTSDATUM
    -0.68
    windowFixed
    -0.68
    DebuggerNonUser
    -0.67
    oulli
    -0.65
    HideFlags
    -0.65
     Baillargeon
    -0.64
    complexContent
    -0.60
    IActionResult
    -0.60
    POSITIVE LOGITS
    árl
    0.53
    ArgsConstructor
    0.53
     déf
    0.48
    BeforeClass
    0.46
     initiale
    0.46
    Dedicated
    0.45
    ungs
    0.44
    æt
    0.43
     Eropa
    0.43
     насељу
    0.43
    Activations Density 0.090%

    No Known Activations