© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific lab procedures and materials

    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
     chimpanze
    -0.53
     cansado
    -0.52
     nvm
    -0.50
     répon
    -0.50
    Erreferentziak
    -0.48
     Breaking
    -0.46
    Breaking
    -0.45
    utnik
    -0.45
    écou
    -0.44
    lägg
    -0.43
    POSITIVE LOGITS
     selection
    1.07
     Selection
    1.02
    selection
    0.98
    Selection
    0.91
     selecting
    0.90
     sélection
    0.86
     Sele
    0.85
     SELECTION
    0.85
     selectable
    0.83
     Selecting
    0.82
    Activations Density 0.126%

    No Known Activations