© 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. 18-RES-MATRYOSHKA-DC
    7. 598
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations associated with the genome

    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.18.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.18.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
    voll
    -0.62
     soñ
    -0.60
     diamants
    -0.57
     tornillos
    -0.56
    tanie
    -0.56
     estren
    -0.55
     seduta
    -0.55
     abiertas
    -0.55
     himſelf
    -0.55
     mence
    -0.55
    POSITIVE LOGITS
    们
    0.69
    们的
    0.67
    們
    0.65
    들의
    0.64
    saraba
    0.59
    DockStyle
    0.57
    sApp
    0.57
     sizes
    0.57
     holders
    0.57
    들
    0.57
    Activations Density 2.280%

    No Known Activations