© 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. 1183
    Prev
    Next
    INDEX
    Explanations

    specific character sequences or coding elements within text data

    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
     gra
    -0.70
     r
    -0.59
     
    -0.59
     par
    -0.57
     g
    -0.56
     tra
    -0.56
     tre
    -0.55
     WE
    -0.53
     z
    -0.53
     f
    -0.51
    POSITIVE LOGITS
     chré
    1.14
     avoient
    1.08
     pouvoit
    1.04
     dévelo
    1.02
     iſt
    1.00
     zelve
    0.98
     feroit
    0.98
     ainfi
    0.97
     auffi
    0.97
     étoient
    0.96
    Activations Density 0.021%

    No Known Activations