© 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. 9455
    Prev
    Next
    INDEX
    Explanations

    conditional statements and checks related to environment variables in a script

    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
    Negative Logits
    ритори
    -0.71
     تضيفلها
    -0.68
    IsMutable
    -0.66
    inkl
    -0.66
    FormTagHelper
    -0.63
    Demografie
    -0.63
    itous
    -0.61
    — 
    -0.59
     Normdatei
    -0.58
    aragus
    -0.57
    POSITIVE LOGITS
     Macedonian
    0.64
    "]);
    0.60
     kaarangay
    0.60
     palindrome
    0.55
     partitions
    0.54
    rawd
    0.53
    andosi
    0.53
     exertions
    0.53
    AutoScaleMode
    0.52
     Septembre
    0.52
    Activations Density 0.014%

    No Known Activations