© 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. 1770
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the initiation of a statement or argument

    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
    Geplaatst
    -1.08
    sizeCache
    -0.92
    migrationBuilder
    -0.85
    المناصب
    -0.84
    IsContent
    -0.84
    verwijspagina
    -0.83
     purpoſe
    -0.83
    MigrationBuilder
    -0.82
     GenerationType
    -0.81
    LEncoder
    -0.81
    POSITIVE LOGITS
    Firstly
    0.90
    abord
    0.88
     Firstly
    0.86
    pierw
    0.85
     firstly
    0.82
    まず
    0.80
    First
    0.75
    Primero
    0.75
     First
    0.75
     primero
    0.72
    Activations Density 0.304%

    No Known Activations