© 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. 22-RES-MATRYOSHKA-DC
    7. 2986
    Prev
    Next
    INDEX
    Explanations

    component identifiers in technical documentation, like figure numbers, part numbers, and layer names

    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
    IUrlHelper
    -0.55
    detectChanges
    -0.51
     sociali
    -0.45
    enderror
    -0.44
    IVEREF
    -0.43
     sappi
    -0.43
    PyTuple
    -0.43
    Viited
    -0.43
    )$}
    -0.42
     виправивши
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.87
     shown
    0.65
     AssemblyCulture
    0.59
    حوالہ
    0.57
    لومات
    0.56
    winston
    0.56
    izr
    0.55
    shown
    0.55
     SwiftUI
    0.53
     Egyptians
    0.52
    Activations Density 0.102%

    No Known Activations