© 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. 19658
    Prev
    Next
    INDEX
    Explanations

    references to diverse groups or categories

    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
     Hens
    -0.81
     Henning
    -0.74
    authorised
    -0.72
    ocks
    -0.70
    ians
    -0.70
    ctuations
    -0.70
    tuuri
    -0.70
    gasus
    -0.69
     Norma
    -0.69
    complexContent
    -0.69
    POSITIVE LOGITS
     Varieties
    0.83
    GOTREF
    0.76
     varieties
    0.71
     Spice
    0.71
     aihe
    0.71
     variety
    0.68
     Winf
    0.67
    دری
    0.67
     subje
    0.67
     Ronde
    0.66
    Activations Density 0.009%

    No Known Activations