© 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. 1448
    Prev
    Next
    INDEX
    Explanations

    mainly geometric shapes and other words related to shapes

    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
    Personendaten
    -0.67
     دیکھیے
    -0.56
    ekan
    -0.50
    </thead>
    -0.47
     findViewById
    -0.45
     AppComponent
    -0.44
     addSubview
    -0.44
    âme
    -0.44
     htons
    -0.44
     Sakai
    -0.44
    POSITIVE LOGITS
     square
    1.16
     circle
    1.15
     circles
    1.09
     triangle
    1.09
     rectangle
    1.06
    square
    1.05
     circular
    1.05
    circle
    1.05
     oval
    1.05
     rectangular
    1.04
    Activations Density 0.975%

    No Known Activations