© 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. 17890
    Prev
    Next
    INDEX
    Explanations

    terms related to open source software

    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
     propOrder
    -0.84
    tagHelperRunner
    -0.82
     CreateTagHelper
    -0.81
    ollectionView
    -0.79
    ModelAdmin
    -0.77
    errHandler
    -0.74
     SwiftUI
    -0.73
     NgModule
    -0.71
    ValueGenerated
    -0.71
    لينكات
    -0.69
    POSITIVE LOGITS
    opensource
    4.31
    Open
    0.66
    Роз
    0.53
    open
    0.52
     Open
    0.52
     Opens
    0.50
     pomen
    0.50
    icordia
    0.49
     presa
    0.49
     OSS
    0.48
    Activations Density 0.000%

    No Known Activations