© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 690
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and related terms

    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
     pok
    -0.50
    moire
    -0.48
    Carriera
    -0.47
    cyn
    -0.47
    InMemory
    -0.45
    ISTRO
    -0.45
     tes
    -0.45
    Quoi
    -0.45
    iosync
    -0.45
    ≪
    -0.44
    POSITIVE LOGITS
     optimization
    1.05
    Optim
    1.02
     optimisation
    0.99
     Optimization
    0.99
     Optim
    0.98
    optim
    0.98
     optim
    0.97
     Optimize
    0.94
    optimization
    0.93
    optimize
    0.93
    Activations Density 1.333%

    No Known Activations