© 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. 31818
    Prev
    Next
    INDEX
    Explanations

    phrases related to access and configuration of resources and systems

    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
    FTC
    -0.53
     ambientales
    -0.50
    tryck
    -0.49
    amera
    -0.48
     Healy
    -0.47
     típicos
    -0.44
     berikut
    -0.44
     gegeven
    -0.44
     erfaring
    -0.43
    jalanan
    -0.42
    POSITIVE LOGITS
    ]")]
    0.85
     CreateTagHelper
    0.82
    OGND
    0.80
     المعيارى
    0.76
     AssemblyCulture
    0.75
     وتسجيلات
    0.75
    contentLoaded
    0.75
    WritableDatabase
    0.75
    EndProject
    0.73
    principalTable
    0.73
    Activations Density 0.185%

    No Known Activations