© 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. 31013
    Prev
    Next
    INDEX
    Explanations

    terms related to concatenation in programming contexts

    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
     AssemblyTitle
    -0.90
     againſt
    -0.89
     Houſe
    -0.88
    ſelves
    -0.87
     ―――――
    -0.83
    ſelf
    -0.82
    ,‎
    -0.82
     ་་
    -0.81
    Geplaatst
    -0.79
     quæ
    -0.78
    POSITIVE LOGITS
    concat
    1.23
     concat
    1.19
     concaten
    1.17
    concaten
    1.09
    Concat
    1.03
     concatenation
    0.96
     concatenate
    0.90
    caten
    0.82
     Baumann
    0.63
    concatenate
    0.59
    Activations Density 0.001%

    No Known Activations