© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    occurrences of terms related to biochemical processes, particularly those involving cell lysis and protein purification

    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
    WebServlet
    -0.54
    CrossRef
    -0.52
     Himo
    -0.52
    ༘
    -0.50
     gulp
    -0.48
     ✭✭
    -0.48
     lein
    -0.48
     geschlossen
    -0.44
     ху
    -0.44
     saites
    -0.43
    POSITIVE LOGITS
     disclosure
    0.79
     open
    0.78
     Disclosure
    0.74
     release
    0.73
    OPEN
    0.73
     ouverte
    0.70
     Liberation
    0.70
     OPEN
    0.70
    Disclosure
    0.70
     openness
    0.69
    Activations Density 0.726%

    No Known Activations