© 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. 11104
    Prev
    Next
    INDEX
    Explanations

    names and terms related to specific individuals or entities in a context, particularly related to Malaysian politics

    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
     ‘
    -0.69
    able
    -0.67
    ette
    -0.65
    اس
    -0.62
    "]}
    -0.61
     Castor
    -0.59
    ”]
    -0.58
    amic
    -0.57
    atic
    -0.56
    a
    -0.56
    POSITIVE LOGITS
     Cah
    1.32
     Kuh
    1.20
     Réponses
    1.16
     Lah
    1.13
     Ruh
    1.12
     Tah
    1.11
     Coh
    1.09
     AH
    1.08
     Ahh
    1.06
    IAH
    1.05
    Activations Density 0.099%

    No Known Activations