© 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. 1422
    Prev
    Next
    INDEX
    Explanations

    toxic chemicals, environmental contamination and the study of it.

    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
    VIAF
    -0.63
    stateProvider
    -0.63
    الحياه
    -0.60
    rikes
    -0.58
     AttributeSet
    -0.57
     عج
    -0.56
     HasFactory
    -0.56
     StatelessWidget
    -0.55
     Compression
    -0.54
    numerusform
    -0.54
    POSITIVE LOGITS
     exposure
    1.18
     toxic
    1.15
     toxicity
    1.08
     Exposure
    1.04
     contaminated
    1.02
     contamination
    1.02
     pollution
    1.00
    exposure
    0.99
     Toxic
    0.99
     carcinogenic
    0.98
    Activations Density 1.372%

    No Known Activations