© 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. 24597
    Prev
    Next
    INDEX
    Explanations

    references to financial implications and policies

    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
    ViewImports
    -0.61
    recht
    -0.49
    ynomial
    -0.49
     domestiques
    -0.47
    Zeneca
    -0.47
     Amts
    -0.47
    isière
    -0.45
     féminin
    -0.44
    таратура
    -0.44
     Conselho
    -0.44
    POSITIVE LOGITS
     незавершена
    1.10
    Portale
    0.88
    XmlAccessorType
    0.83
    tagHelperRunner
    0.78
     Мексичка
    0.68
    AddTagHelper
    0.68
    MemoryWarning
    0.65
    География
    0.65
    WithIOException
    0.63
     اطلع
    0.63
    Activations Density 0.303%

    No Known Activations