© 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. 461
    Prev
    Next
    INDEX
    Explanations

    concepts of correlation and interconnectedness among different themes or categories

    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
    orteur
    -0.59
    setupUi
    -0.59
     polvere
    -0.53
     يتيمه
    -0.52
    caid
    -0.52
     retra
    -0.51
     lampada
    -0.51
     Holman
    -0.51
    ⃗
    -0.51
     Wiseman
    -0.49
    POSITIVE LOGITS
     between
    1.59
    between
    1.45
     между
    1.41
     Between
    1.36
    Between
    1.29
     BETWEEN
    1.29
     antara
    1.25
     між
    1.22
     betwixt
    1.16
     pomiędzy
    1.15
    Activations Density 3.189%

    No Known Activations