© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so."

    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
    μία
    -0.81
     Winfrey
    -0.77
    Portail
    -0.75
    indépendance
    -0.75
    Freeman
    -0.73
     Honduras
    -0.73
     Flemish
    -0.72
     Hond
    -0.71
     Jüng
    -0.71
    intellij
    -0.71
    POSITIVE LOGITS
     So
    1.45
     so
    1.40
    So
    1.38
     SO
    1.27
    so
    1.13
    Sooo
    1.05
    SO
    1.04
     Så
    0.90
    Convey
    0.82
     sooo
    0.81
    Activations Density 0.555%

    No Known Activations