© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 29259
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the necessity or urgency related to tasks and execution

    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
    Negative Logits
    
    -0.64
     "..\..\..\
    -0.57
    िखित
    -0.56
     BadRequest
    -0.54
     "..\..\
    -0.54
    webElement
    -0.51
    CREATED
    -0.50
    حياته
    -0.50
    zac
    -0.49
    ofar
    -0.49
    POSITIVE LOGITS
    enterOuterAlt
    0.73
     typelib
    0.72
    LookAnd
    0.65
    EndGlobalSection
    0.62
    __(/*!
    0.57
    ChildScrollView
    0.55
    resave
    0.54
    ]++;
    0.54
    RenderAtEndOf
    0.53
    BeginContext
    0.53
    Activations Density 0.112%

    No Known Activations