© 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. 22-RES-MATRYOSHKA-DC
    7. 2754
    Prev
    Next
    INDEX
    Explanations

    scientific research paper measurements and related terms

    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.22.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.22.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
     suitability
    -0.68
     performance
    -0.67
     efficacy
    -0.65
     viability
    -0.65
     effectiveness
    -0.62
     ability
    -0.61
    performance
    -0.59
     quantify
    -0.59
     efficiency
    -0.59
     behaviour
    -0.59
    POSITIVE LOGITS
    EndContext
    0.61
    netinet
    0.60
    SequentialGroup
    0.55
    TagMode
    0.50
    enderror
    0.50
     HttpNotFound
    0.50
    chtet
    0.49
    cornerRadius
    0.49
    recursion
    0.49
    ArrayAdapter
    0.49
    Activations Density 0.812%

    No Known Activations