© 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. 17608
    Prev
    Next
    INDEX
    Explanations

    references to specific compounds or chemicals related to health

    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
     &___
    -0.87
     متعلقه
    -0.82
    ValueStyle
    -0.82
     Hano
    -0.81
     Quo
    -0.81
    〉
    -0.80
     >=",
    -0.79
     Charlene
    -0.78
    ENTIALS
    -0.75
    OGND
    -0.74
    POSITIVE LOGITS
     CH
    1.04
    ly
    0.94
     Vah
    0.85
    CH
    0.82
     Landis
    0.81
    TH
    0.80
    TR
    0.79
    y
    0.72
    ology
    0.71
    ᴅ
    0.70
    Activations Density 0.025%

    No Known Activations