© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5726
    Prev
    Next
    INDEX
    Explanations

    formal references to research studies or patents

    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
    Tikang
    -0.58
    OGND
    -0.57
     wireType
    -0.57
    ]='\
    -0.56
     BoxDecoration
    -0.54
    +#+#
    -0.50
    stridium
    -0.50
     initComponents
    -0.50
    énagement
    -0.49
    MemoryWarning
    -0.49
    POSITIVE LOGITS
     препратки
    0.54
    ngdoc
    0.51
     themselves
    0.49
    ddots
    0.49
    ünste
    0.48
    ……"
    0.48
     authors
    0.48
     podjela
    0.47
    ristan
    0.45
    참고
    0.45
    Activations Density 0.723%

    No Known Activations