© 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. 32184
    Prev
    Next
    INDEX
    Explanations

    sections of HTML or XML code

    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
     Aene
    -0.47
    Armand
    -0.47
     settle
    -0.46
     Murat
    -0.45
     Koffer
    -0.45
     mencakup
    -0.44
    Jeb
    -0.44
     quanh
    -0.44
     Jeb
    -0.44
     później
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    1.02
    RegressionTest
    0.90
    invokeLater
    0.86
    +#+#
    0.81
    __':
    0.79
     resourceCulture
    0.78
    __":
    0.78
    tonode
    0.77
     ExecuteAsync
    0.75
     مشين
    0.74
    Activations Density 0.013%

    No Known Activations