© 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. 4175
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate contrasting or additional information

    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
     الرياضيه
    -1.00
     CreateTagHelper
    -0.98
    mybatisplus
    -0.84
     aDecoder
    -0.77
     kaarangay
    -0.73
     utafitiHapana
    -0.71
     mínimos
    -0.71
    inheritDoc
    -0.70
     betweenstory
    -0.67
    sibilità
    -0.66
    POSITIVE LOGITS
    PreferredItem
    0.63
     usually
    0.59
     subject
    0.58
     is
    0.57
    且
    0.57
     self
    0.56
     highly
    0.56
    zuli
    0.55
     very
    0.52
     clear
    0.52
    Activations Density 0.270%

    No Known Activations