© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3697
    Prev
    Next
    INDEX
    Explanations

    specific types of processor instructions and their associated names or identifiers

    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
    INSEE
    -0.63
     Silla
    -0.53
    أس
    -0.53
    arvi
    -0.52
    rippa
    -0.52
     Esch
    -0.48
     Reproduce
    -0.48
     HN
    -0.48
     SANS
    -0.48
    ัติ
    -0.48
    POSITIVE LOGITS
     snippetHide
    0.74
    BorderFactory
    0.68
     localObject
    0.66
     GetEnumerator
    0.63
    typeorm
    0.62
     autorytatywna
    0.61
     newBuilder
    0.59
    Tracce
    0.59
    usermodel
    0.57
    ExecutionContext
    0.56
    Activations Density 0.021%

    No Known Activations