© 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. 9310
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures involving parameters in coding functions

    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
     half
    -0.51
     will
    -0.50
     was
    -0.48
     medio
    -0.46
     its
    -0.46
     the
    -0.45
     unknownFields
    -0.45
    ژ
    -0.45
     can
    -0.44
     سر
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.92
     FetchType
    0.79
     "@/
    0.72
     Majefty
    0.71
     pleaſure
    0.68
     Houſe
    0.66
     clearColor
    0.65
     TimeUnit
    0.65
    featureID
    0.65
    uintptr
    0.65
    Activations Density 0.103%

    No Known Activations