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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5245
    Prev
    Next
    INDEX
    Explanations

    sequences that describe various embodiments of an invention or method

    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
    tagHelperRunner
    -0.68
    DllImport
    -0.63
    InitVars
    -0.59
    AutoField
    -0.56
    enumi
    -0.54
    oredCriteria
    -0.54
     BorderRadius
    -0.52
    mbggenerated
    -0.52
     "..\..\..\
    -0.52
    XmlAccessorType
    -0.50
    POSITIVE LOGITS
     становника
    0.71
    الإنجليزية
    0.70
    HasForeignKey
    0.65
     kasarigan
    0.55
    ropical
    0.52
     zatrzy
    0.51
    catraz
    0.51
    numerusform
    0.50
     Exactos
    0.50
     philosophie
    0.49
    Activations Density 0.104%

    No Known Activations