© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to SEO and Google.

    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
    ConstraintMaker
    -0.82
    RectangleBorder
    -0.75
     actionTypes
    -0.66
    SequentialGroup
    -0.64
    BeginContext
    -0.62
    SharedCtor
    -0.61
    FXMLLoader
    -0.59
    hésitez
    -0.59
     onData
    -0.59
    SafeMath
    -0.57
    POSITIVE LOGITS
     ranking
    0.71
     indexed
    0.66
     Ranking
    0.65
     crawling
    0.64
     index
    0.63
     rank
    0.63
     indexing
    0.63
     robots
    0.62
    index
    0.60
    rank
    0.60
    Activations Density 0.088%

    No Known Activations