© 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. 24-RES-MATRYOSHKA-DC
    7. 251
    Prev
    Next
    INDEX
    Explanations

    words that relate to importance/exclusivity

    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.24.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.24.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
     législation
    -0.57
     tärke
    -0.54
     malheure
    -0.51
     ważne
    -0.50
     réglementation
    -0.50
    Див
    -0.50
     fontos
    -0.49
     pelbagai
    -0.49
    感兴趣
    -0.49
     mniej
    -0.49
    POSITIVE LOGITS
     reliability
    1.21
     accuracy
    1.20
     consistency
    1.13
     effectiveness
    1.11
     simplicity
    1.09
     completeness
    1.09
     practicality
    1.09
     efficiency
    1.07
     authenticity
    1.07
     robustness
    1.07
    Activations Density 3.519%

    No Known Activations