© 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. 2565
    Prev
    Next
    INDEX
    Explanations

    patterns related to structured data formats like JSON or programming syntax

    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
    Enllaces
    -0.49
    ++];
    -0.48
    Diweddarwch
    -0.46
     Plu
    -0.45
    ார
    -0.45
    COMPLE
    -0.45
    heav
    -0.45
    Plu
    -0.45
    וויק
    -0.45
    DllImport
    -0.44
    POSITIVE LOGITS
    ">—
    0.93
    Vidite
    0.75
    IsMutable
    0.71
    enoord
    0.69
     للمعارف
    0.67
     gereken
    0.66
    seamnă
    0.66
     تانيه
    0.66
    typeorm
    0.64
     estimés
    0.63
    Activations Density 0.329%

    No Known Activations