© 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. 28429
    Prev
    Next
    INDEX
    Explanations

    bracketed code structures or syntax

    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
    WebVitals
    -0.56
    RectangleBorder
    -0.54
    HomeAsUpEnabled
    -0.51
     uncer
    -0.48
     NSCoder
    -0.47
    #+#
    -0.47
    روید
    -0.45
    AFE
    -0.43
    mi
    -0.43
    QtWidgets
    -0.43
    POSITIVE LOGITS
    transQ
    0.72
    RegressionTest
    0.70
     internetowa
    0.68
    ^(@)
    0.66
     <=",
    0.66
    LookAnd
    0.65
     "..\..\
    0.65
     通販
    0.63
    fromnode
    0.63
     صوتيه
    0.62
    Activations Density 0.009%

    No Known Activations