© 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. 6346
    Prev
    Next
    INDEX
    Explanations

    data structures and formatting related to tables or graphical representations

    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
    躇
    -0.55
    tvguidetime
    -0.52
     AssemblyCompany
    -0.50
    Proof
    -0.48
    edra
    -0.47
    lihatkan
    -0.44
    fifths
    -0.44
     ск
    -0.43
    XmlAccessType
    -0.43
     Proof
    -0.42
    POSITIVE LOGITS
    principalTable
    0.67
    AtIndexPath
    0.67
     AspNetCore
    0.65
     _$
    0.62
    ColumnHeaders
    0.62
     tassels
    0.59
    XmlEnum
    0.59
     (°
    0.58
     onOptions
    0.58
     réalis
    0.57
    Activations Density 0.130%

    No Known Activations