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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9759
    Prev
    Next
    INDEX
    Explanations

    references to input/output reader classes or methods

    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
     Commandant
    -0.62
     Modesto
    -0.62
     Adkins
    -0.60
    klá
    -0.60
     vestiti
    -0.60
    kjø
    -0.59
    Mons
    -0.59
     Strickland
    -0.58
     Corbu
    -0.58
     LeBlanc
    -0.58
    POSITIVE LOGITS
     Reader
    1.34
    Reader
    1.24
     Readers
    1.19
     reader
    1.13
    Readers
    1.11
    reader
    1.07
     readers
    1.07
    readers
    0.98
     READER
    0.95
     FileReader
    0.94
    Activations Density 0.010%

    No Known Activations