© 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. 20125
    Prev
    Next
    INDEX
    Explanations

    declarations of functions 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
    ]")]
    -0.63
    nonatomic
    -0.62
    DeleteBehavior
    -0.61
    XmlType
    -0.59
    RTHOOK
    -0.59
     empêcher
    -0.59
    djangoproject
    -0.59
    registrer
    -0.59
     ſmall
    -0.57
     uſed
    -0.57
    POSITIVE LOGITS
    FetchType
    0.77
    AnchorStyles
    0.71
    HomeAsUpEnabled
    0.70
    RAINT
    0.68
    GHIJKLM
    0.63
    findOrFail
    0.60
    ęku
    0.59
    Storyboard
    0.57
     drinker
    0.57
    ể
    0.57
    Activations Density 0.011%

    No Known Activations