© 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. 26538
    Prev
    Next
    INDEX
    Explanations

    references to loop control variables often used in programming, specifically integer variables

    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
    IsContent
    -0.96
    ExtendWith
    -0.87
    ={`/
    -0.82
    LookAnd
    -0.80
     gynhyrchwyd
    -0.80
     '\\;'
    -0.80
    enumi
    -0.79
     ostavi
    -0.79
     Roskov
    -0.77
    __))
    -0.77
    POSITIVE LOGITS
    SEMICOLON
    0.61
     x
    0.52
    roff
    0.46
    chka
    0.46
     I
    0.46
    wür
    0.45
     culturelles
    0.45
    רב
    0.44
    nial
    0.44
     cặp
    0.44
    Activations Density 0.006%

    No Known Activations