© 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. 12-RES-MATRYOSHKA-DC
    7. 4051
    Prev
    Next
    INDEX
    Explanations

    instances of the word "infection" and related terms

    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
     referenties
    -0.85
     NSM
    -0.81
     createSprite
    -0.81
     plotly
    -0.76
     Rha
    -0.73
    ⓧ
    -0.73
    ificance
    -0.73
    drawal
    -0.73
     Yule
    -0.73
    ylase
    -0.72
    POSITIVE LOGITS
     infection
    1.10
     Infections
    1.09
     infections
    1.05
     Infection
    1.03
    infection
    1.03
     infect
    0.99
    infected
    0.98
    FECTION
    0.97
    Infection
    0.96
     infected
    0.95
    Activations Density 0.039%

    No Known Activations