Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 25185
    Prev
    Next
    INDEX
    Explanations

    phrases or references related to structural elements or frameworks

    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
    RegressionTest
    -0.51
    致
    -0.49
    ymus
    -0.45
    Pro
    -0.44
     про
    -0.44
     Те
    -0.44
    hol
    -0.42
    鰭
    -0.42
    Share
    -0.42
    taglio
    -0.41
    POSITIVE LOGITS
    MemoryWarning
    0.92
    OptionsMenu
    0.90
    CloseOperation
    0.88
    bootstrapcdn
    0.84
     يتيمه
    0.82
     Вікіпе
    0.81
    󠁢
    0.80
    SpringBootTest
    0.79
    principalColumn
    0.78
    WebVitals
    0.77
    Activations Density 0.062%

    No Known Activations