© 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. 24-RES-MATRYOSHKA-DC
    7. 657
    Prev
    Next
    INDEX
    Explanations

    descriptions of experimental methodology.

    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
     betweenstory
    -0.64
     initComponents
    -0.62
    TagMode
    -0.59
     transférez
    -0.57
     resourceCulture
    -0.56
    Климат
    -0.56
    itives
    -0.56
    Czytaj
    -0.55
     adopt
    -0.55
     }^{[
    -0.54
    POSITIVE LOGITS
     character
    0.84
    Understand
    0.77
     Understand
    0.76
    character
    0.76
     Determine
    0.75
     determine
    0.75
     Character
    0.73
     understand
    0.73
     Assess
    0.72
    Determine
    0.71
    Activations Density 0.434%

    No Known Activations