© 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. 15423
    Prev
    Next
    INDEX
    Explanations

    terms related to neural networks and their architecture

    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
     teaspoons
    -0.77
     resourceCulture
    -0.77
    keo
    -0.76
     Sabrina
    -0.72
    intu
    -0.70
     infanti
    -0.70
     Cosmo
    -0.69
    bek
    -0.68
     CreateTagHelper
    -0.68
    oredCriteria
    -0.68
    POSITIVE LOGITS
    Neural
    1.17
     Neural
    1.15
    neural
    1.13
     neural
    1.10
    شاركة
    0.79
    Mell
    0.74
    ages
    0.72
    PathVariable
    0.69
     muun
    0.69
     Emery
    0.69
    Activations Density 0.002%

    No Known Activations