© 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. 19780
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and inquiries about well-being

    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
     pro
    -0.49
    isse
    -0.44
    don
    -0.44
     zal
    -0.43
    tschaft
    -0.43
     ganado
    -0.42
    돈
    -0.42
    ENTI
    -0.41
    ikt
    -0.40
    hili
    -0.40
    POSITIVE LOGITS
    CloseOperation
    0.96
     itſelf
    0.89
     <>",
    0.82
    WriteTagHelper
    0.79
     Paglinawan
    0.79
     ſind
    0.77
    المناصب
    0.77
     GenerationType
    0.76
    awakeFromNib
    0.75
    WithIOException
    0.73
    Activations Density 0.056%

    No Known Activations