© 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. 1429
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing collective participation or inclusion

    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
     Goy
    -0.68
     Nef
    -0.68
     amb
    -0.66
    Nef
    -0.63
     pinos
    -0.63
     some
    -0.60
     li
    -0.60
     Bon
    -0.60
    buster
    -0.58
    stringify
    -0.57
    POSITIVE LOGITS
    EACH
    1.77
     EACH
    1.70
    each
    1.56
     each
    1.53
     Each
    1.53
    Each
    1.51
    Chaque
    1.51
     Chaque
    1.37
     Ogni
    1.36
     chaque
    1.28
    Activations Density 0.236%

    No Known Activations