© 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. 18-RES-MATRYOSHKA-DC
    7. 229
    Prev
    Next
    INDEX
    Explanations

    discussions of abstract existential problems such as code parsing issues, ethics, morals, and historical conflicts.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     itſelf
    -1.17
    berdayakan
    -1.15
     déchir
    -1.11
     ainfi
    -1.11
     Theſe
    -1.09
     ―――――
    -1.08
     myſelf
    -1.08
     Monfieur
    -1.06
     doubtnut
    -1.06
     auffi
    -1.05
    POSITIVE LOGITS
     Nowadays
    1.02
    Nowadays
    0.96
     nowadays
    0.91
     «
    0.89
     advices
    0.85
     Moreover
    0.82
     planification
    0.78
    Moreover
    0.78
     informations
    0.77
     i
    0.75
    Activations Density 8.434%

    No Known Activations