© 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. 30484
    Prev
    Next
    INDEX
    Explanations

    identifiers and specific terms related to coding or data formatting

    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
     ditulis
    -0.56
    inSlope
    -0.52
    inée
    -0.50
    ждый
    -0.47
     ispir
    -0.47
    AccessorTable
    -0.46
     portátiles
    -0.46
    ждую
    -0.44
     "<?
    -0.43
     gambe
    -0.43
    POSITIVE LOGITS
    BeginContext
    0.93
     numbered
    0.84
     محفوظة
    0.81
    enumii
    0.79
     XNUMX
    0.77
    FontOfSize
    0.77
     оригіналу
    0.76
    yntaxException
    0.75
     estimés
    0.75
     numbering
    0.73
    Activations Density 0.219%

    No Known Activations