© 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. 22018
    Prev
    Next
    INDEX
    Explanations

    references to digital objects like articles or online materials

    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
    sidemargin
    -0.77
     myſelf
    -0.71
    UserScript
    -0.71
     utafitiHapana
    -0.68
     itſelf
    -0.67
    ьаж
    -0.66
    yntaxException
    -0.66
    ſelf
    -0.65
    ſelves
    -0.64
     himſelf
    -0.63
    POSITIVE LOGITS
    TagMode
    0.69
     cap
    0.53
     mis
    0.53
    Datuak
    0.52
     par
    0.51
    ffffffff
    0.50
    Παραπομπές
    0.49
    SwingConstants
    0.49
    iant
    0.49
     bet
    0.47
    Activations Density 0.017%

    No Known Activations