© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2153
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or contemplation about identity and experience

    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
     unut
    -0.65
     cauſe
    -0.62
     caufe
    -0.57
     administra
    -0.56
     évêque
    -0.56
     yı
    -0.54
    braun
    -0.54
     exceptionnelle
    -0.54
     Bär
    -0.54
     lapar
    -0.53
    POSITIVE LOGITS
    Kinda
    0.99
     sorta
    0.98
     Kinda
    0.91
    GroupLayout
    0.90
    complexContent
    0.85
    kinda
    0.83
     Reverso
    0.81
     quasi
    0.76
     рода
    0.76
    EndInit
    0.75
    Activations Density 0.127%

    No Known Activations