© 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. 29662
    Prev
    Next
    INDEX
    Explanations

    The presence of ampersands in various contexts, particularly in coding or syntactical structures

    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
    mstyle
    -0.65
    opoulos
    -0.62
    PZ
    -0.59
    se
    -0.58
    ดี
    -0.58
    lük
    -0.57
     igr
    -0.56
    pi
    -0.55
     Berkeley
    -0.54
    ambi
    -0.54
    POSITIVE LOGITS
     فريبيس
    0.85
     المعيارى
    0.83
    elemField
    0.82
     rhestr
    0.80
    IVEREF
    0.78
    writeFieldEnd
    0.75
     lenker
    0.73
    MemoryWarning
    0.73
     ALICE
    0.73
    XtraEditors
    0.72
    Activations Density 0.005%

    No Known Activations