© 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. 16472
    Prev
    Next
    INDEX
    Explanations

    references to conferences and conference-related events

    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
     poros
    -0.73
    ut
    -0.72
    stav
    -0.68
    setForeground
    -0.68
     sot
    -0.68
    so
    -0.66
    otus
    -0.66
     pasti
    -0.65
     Sox
    -0.65
    ness
    -0.64
    POSITIVE LOGITS
     conferences
    1.41
     Conferences
    1.36
     conference
    1.21
     Conference
    1.20
    Conference
    1.20
     conferencia
    1.13
     CONFERENCE
    1.12
    conference
    1.08
     Conferencia
    1.06
    FERENCE
    1.05
    Activations Density 0.006%

    No Known Activations