© 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. 22-RES-MATRYOSHKA-DC
    7. 2801
    Prev
    Next
    INDEX
    Explanations

    HTML `data-` attributes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     collation
    -0.91
     collected
    -0.85
     mergeFrom
    -0.85
    ########.
    -0.84
     dAtA
    -0.81
     متعلقه
    -0.80
     Wikispecies
    -0.77
     gathered
    -0.76
    DrawerToggle
    -0.76
     Efq
    -0.75
    POSITIVE LOGITS
    WEBPACK
    0.53
    factor
    0.45
     factor
    0.40
    當
    0.40
    aos
    0.40
    
    0.40
     G
    0.39
    makaian
    0.38
     R
    0.38
     /
    0.37
    Activations Density 0.060%

    No Known Activations