© 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. 461
    Prev
    Next
    INDEX
    Explanations

    properties and property values in JSON objects

    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
     bestaande
    -0.52
     eukaryotic
    -0.50
     Geller
    -0.49
     homomorphism
    -0.49
     existentes
    -0.47
     vostri
    -0.47
    WithMany
    -0.47
     fibroblast
    -0.46
     benthic
    -0.46
     ;(
    -0.45
    POSITIVE LOGITS
     type
    0.93
     description
    0.92
     name
    0.88
     id
    0.80
    type
    0.78
    description
    0.77
     version
    0.73
     title
    0.71
     status
    0.70
     resultCode
    0.68
    Activations Density 3.634%

    No Known Activations