© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 246
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and assembly processes

    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
     N
    -0.69
     E
    -0.64
    czaj
    -0.62
    Subviews
    -0.61
    ̣ng
    -0.61
     
    -0.61
     X
    -0.59
    N
    -0.59
    исленность
    -0.59
    újo
    -0.59
    POSITIVE LOGITS
     Efq
    1.27
    ſelf
    1.08
     Monfieur
    1.06
     whoſe
    1.05
     Theſe
    1.05
     myſelf
    1.05
     houſe
    1.03
     ſy
    1.00
     Mover
    1.00
     Anſ
    0.97
    Activations Density 2.472%

    No Known Activations