© 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. 12-RES-MATRYOSHKA-DC
    7. 1320
    Prev
    Next
    INDEX
    Explanations

    key concepts and phrases indicating significance in research findings or conclusions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    tinyos
    -0.67
     paco
    -0.63
     Fels
    -0.61
    )}=
    -0.59
    كا
    -0.57
                                   
    -0.55
    ))}
    -0.54
     aggressive
    -0.54
     "'";
    -0.54
     corde
    -0.53
    POSITIVE LOGITS
     main
    1.58
     MAIN
    1.57
    MAIN
    1.42
     Main
    1.41
     principale
    1.38
    Main
    1.34
     Haupt
    1.25
     głów
    1.24
     principal
    1.23
     mains
    1.23
    Activations Density 0.263%

    No Known Activations