© 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. 15553
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to accuracy and ensuring information reliability

    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
    exitRule
    -0.64
    IGraphics
    -0.60
    DockStyle
    -0.59
    ScopeManager
    -0.59
     useSelector
    -0.58
    abetes
    -0.57
    openzeppelin
    -0.56
    WebControls
    -0.55
    WebServlet
    -0.54
    WebVitals
    -0.54
    POSITIVE LOGITS
     accuracy
    0.68
     completeness
    0.58
    othea
    0.57
     continuity
    0.57
     inaccuracies
    0.57
    vician
    0.54
     errors
    0.52
     reliability
    0.51
     Accuracy
    0.51
     непре
    0.51
    Activations Density 0.007%

    No Known Activations