© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4188
    Prev
    Next
    INDEX
    Explanations

    technical specifications or data related to software or code snippets

    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
     chré
    -0.82
    __(/*!
    -0.81
     дописавши
    -0.78
     asiatique
    -0.69
    providedIn
    -0.67
     Cæsar
    -0.65
     grecque
    -0.65
     chrétien
    -0.65
     lachen
    -0.64
     chrétienne
    -0.63
    POSITIVE LOGITS
    AccessorTable
    0.55
     PackageManager
    0.49
     ActionBar
    0.44
    ade
    0.44
    ential
    0.43
    grafic
    0.43
    AddTagHelper
    0.42
    asteroide
    0.42
    )|^{
    0.40
    erd
    0.40
    Activations Density 0.170%

    No Known Activations