© 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. 17526
    Prev
    Next
    INDEX
    Explanations

    references to large data files and their complexities

    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
    ImageContext
    -0.68
    iecie
    -0.54
     AssemblyVersion
    -0.53
    GIVEREF
    -0.52
    uurs
    -0.52
    UnitTesting
    -0.51
    bouts
    -0.50
    vallis
    -0.50
    尼斯
    -0.50
     تضيفلها
    -0.49
    POSITIVE LOGITS
     alphabetically
    0.65
    حياتها
    0.61
     deluge
    0.56
    حياته
    0.55
    OGND
    0.55
     avalanche
    0.51
     hundreds
    0.50
    hundreds
    0.50
    ırl
    0.48
     Tribut
    0.48
    Activations Density 0.098%

    No Known Activations