© 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. 2277
    Prev
    Next
    INDEX
    Explanations

    words related to microbes, cellular biology, and the chemical processes associated with their existence

    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
     ggf
    -0.59
     evtl
    -0.54
    didSet
    -0.53
    又は
    -0.50
     zij
    -0.50
     ایشان
    -0.50
    posedge
    -0.47
     Subsequently
    -0.47
     рекомендуется
    -0.47
     sicherlich
    -0.46
    POSITIVE LOGITS
     estimés
    0.85
     billions
    0.81
     millions
    0.78
    matchCondition
    0.76
    millions
    0.73
    IUrlHelper
    0.73
     Millions
    0.70
     صوتيه
    0.70
     molecules
    0.69
     Cientí
    0.69
    Activations Density 0.844%

    No Known Activations