© 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. 20123
    Prev
    Next
    INDEX
    Explanations

    sections or markers within code or document structures

    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
    ILON
    -0.70
    THM
    -0.66
    StringProperty
    -0.65
    ReadInt
    -0.63
     Bader
    -0.63
    uride
    -0.63
    ProgressHUD
    -0.61
    udic
    -0.60
     Bü
    -0.60
    rungsseite
    -0.60
    POSITIVE LOGITS
    ('=
    0.87
    .=
    0.73
     vectorielles
    0.73
    /=
    0.73
    انجليز
    0.73
     fays
    0.70
    ("="
    0.68
     "=
    0.66
    >=</
    0.65
    "><?=
    0.65
    Activations Density 0.048%

    No Known Activations