© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    mentions of issues spreading to more than one location

    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
     متعلقه
    -0.65
     protoimpl
    -0.65
    tagHelperRunner
    -0.61
    KommentareTeilen
    -0.58
     ImportError
    -0.57
    providedIn
    -0.53
    tdessen
    -0.53
    IMPORTED
    -0.52
    expandindo
    -0.52
    WriteTagHelper
    -0.52
    POSITIVE LOGITS
     fast
    3.00
    fast
    2.66
     faster
    2.64
     Fast
    2.53
    Fast
    2.52
     quickly
    2.45
     quick
    2.44
     FAST
    2.39
     fastest
    2.36
     quicker
    2.34
    Activations Density 0.741%

    No Known Activations