© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5333
    Prev
    Next
    INDEX
    Explanations

    words related to health, particularly those associated with gastrointestinal and oncological topics

    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
     confiable
    -1.06
     theaters
    -1.05
     parlor
    -1.04
     favors
    -0.98
    veled
    -0.93
     flavors
    -0.93
     flavorful
    -0.93
     theater
    -0.92
     favorably
    -0.92
     mustache
    -0.92
    POSITIVE LOGITS
    Whilst
    1.48
     Whilst
    1.45
     realised
    1.43
     specialises
    1.41
     recognised
    1.40
     realise
    1.38
    centre
    1.38
     tyres
    1.38
     Organisations
    1.37
    COLOUR
    1.37
    Activations Density 2.261%

    No Known Activations