© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1117
    Prev
    Next
    INDEX
    Explanations

    the prefix "bio-" related to biological or environmental processes

    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
    قایناقلار
    -0.64
    woofer
    -0.57
     oseb
    -0.54
     correctes
    -0.54
     Gästen
    -0.54
     résolution
    -0.54
     automatiques
    -0.53
     Unsc
    -0.53
    Provision
    -0.53
     quæ
    -0.53
    POSITIVE LOGITS
     bio
    0.96
     Bio
    0.88
     BIO
    0.68
    Bio
    0.68
     plau
    0.61
     bios
    0.59
     био
    0.58
    logically
    0.55
    bio
    0.53
    ;++
    0.53
    Activations Density 0.068%

    No Known Activations