© 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. 31965
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and symbols in code snippets

    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
    ellido
    -0.82
     Normdatei
    -0.69
    creativecommons
    -0.66
    erokee
    -0.65
     Schult
    -0.63
     ADN
    -0.61
    setOutput
    -0.61
     createSprite
    -0.61
    发表于
    -0.60
    ...@
    -0.60
    POSITIVE LOGITS
    ¦
    1.24
     ¦
    0.98
     Bubbles
    0.72
     Seizures
    0.71
    bbene
    0.69
     TokenType
    0.69
    bcryptjs
    0.69
     lexer
    0.69
     seizures
    0.67
     Sympathy
    0.67
    Activations Density 0.000%

    No Known Activations