© 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. 8861
    Prev
    Next
    INDEX
    Explanations

    JSON-related structures and data in code

    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
    ">//
    -0.96
    IntoConstraints
    -0.78
     виправивши
    -0.76
    routeProvider
    -0.71
    DockStyle
    -0.71
    AnchorStyles
    -0.71
     sumpay
    -0.70
    StoryboardSegue
    -0.68
     SIMBAD
    -0.67
    Controllo
    -0.65
    POSITIVE LOGITS
    ācija
    0.49
    RequestBody
    0.47
    Facades
    0.41
    дә
    0.39
    Batis
    0.39
    ;&
    0.38
     ayakkab
    0.38
    artes
    0.38
     Neub
    0.38
    Filed
    0.38
    Activations Density 0.082%

    No Known Activations