© 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. 15990
    Prev
    Next
    INDEX
    Explanations

    questions about problem-solving and decision-making

    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
    tagHelperRunner
    -0.60
    FormTagHelper
    -0.57
     samarbeid
    -0.54
     uintptr
    -0.48
    principalTable
    -0.46
     sebelumnya
    -0.45
    farin
    -0.45
     الرياضيه
    -0.42
     myö
    -0.42
     ComVisible
    -0.41
    POSITIVE LOGITS
    findpost
    0.79
     lautet
    0.62
     المعيارى
    0.58
     الحره
    0.57
    GeneratedValue
    0.55
     pageContext
    0.54
    PHeader
    0.53
    errHandler
    0.52
    akyti
    0.52
     motto
    0.52
    Activations Density 0.107%

    No Known Activations