© 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. 19699
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and returns

    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
     betweenstory
    -1.21
    parsedMessage
    -0.94
    setVerticalGroup
    -0.81
     SwitchCompat
    -0.73
    ArrowToggle
    -0.70
    AsUp
    -0.69
    principalTable
    -0.68
    bewerken
    -0.68
     виправивши
    -0.68
    AndEndTag
    -0.68
    POSITIVE LOGITS
     BoxDecoration
    0.72
     Efq
    0.71
    ^(@)
    0.70
     appunto
    0.66
     houſe
    0.65
     poffe
    0.63
     ExecuteAsync
    0.62
     perfons
    0.62
     Houſe
    0.60
     OMITTED
    0.60
    Activations Density 1.827%

    No Known Activations