© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21927
    Prev
    Next
    INDEX
    Explanations

    percentages related to concentrations or dilutions in experimental contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Smar
    -0.52
     theoretical
    -0.48
    perten
    -0.46
    ことです
    -0.45
    theoretical
    -0.45
    Theoretical
    -0.43
     cal
    -0.43
    assertEquals
    -0.43
     pat
    -0.42
    nmgp
    -0.42
    POSITIVE LOGITS
    ISupport
    0.90
    principalColumn
    0.89
    sizeCache
    0.87
     pleaſure
    0.81
     lenker
    0.77
    kháu
    0.77
    EndGlobalSection
    0.76
    SharedDtor
    0.76
    tagHelperRunner
    0.75
     cherchés
    0.73
    Activations Density 0.009%

    No Known Activations