© 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. 20946
    Prev
    Next
    INDEX
    Explanations

    references to virtual machine (VM) identifiers and their statuses

    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
     stiefel
    -0.91
     jLabel
    -0.84
     Thackeray
    -0.79
     Clarion
    -0.78
     quæ
    -0.77
     Ith
    -0.77
     snippetHide
    -0.76
     Roskov
    -0.75
    RefNanny
    -0.75
    parseLong
    -0.75
    POSITIVE LOGITS
     vm
    1.23
     VM
    1.14
    vm
    1.11
     VMs
    0.96
    VM
    0.95
    vms
    0.76
    robat
    0.73
    machines
    0.68
     Post
    0.68
     Vm
    0.66
    Activations Density 0.005%

    No Known Activations