© 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. 8704
    Prev
    Next
    INDEX
    Explanations

    phrases related to errors and failure in certificate and password processing

    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
    InputBorder
    -0.59
     Meksiku
    -0.52
    webElementXpaths
    -0.52
    دانشنامهٔ
    -0.52
    RegressionTest
    -0.52
     onlyOwner
    -0.50
    المناصب
    -0.50
    OGND
    -0.49
    STROKE
    -0.49
    FileVersion
    -0.48
    POSITIVE LOGITS
     createState
    0.69
    stdafx
    0.68
    SequentialGroup
    0.62
     instead
    0.59
     viewDidLoad
    0.58
    cemment
    0.57
    mapStateToProps
    0.56
    inflater
    0.56
     ioutil
    0.56
     Instead
    0.55
    Activations Density 0.005%

    No Known Activations