© 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. 24-RES-MATRYOSHKA-DC
    7. 1249
    Prev
    Next
    INDEX
    Explanations

    HTML or Javascript related to plus or minus buttons that are clickable

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
    QMetaType
    -0.65
    IsPostBack
    -0.59
     ExecuteAsync
    -0.59
    ChildScrollView
    -0.56
    GUILayout
    -0.55
    NameInMap
    -0.55
    WebKit
    -0.54
     SEDS
    -0.53
    setVerticalGroup
    -0.52
    rophoresis
    -0.52
    POSITIVE LOGITS
     icon
    1.01
    icon
    0.96
     Icon
    0.92
     symbol
    0.85
     icons
    0.85
    Icon
    0.82
     ICON
    0.81
     Symbol
    0.73
     fa
    0.72
    ICON
    0.72
    Activations Density 0.354%

    No Known Activations