© 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. 12-RES-MATRYOSHKA-DC
    7. 29913
    Prev
    Next
    INDEX
    Explanations

    phrases indicating new research findings or unique contributions to scientific knowledge

    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
     ever
    -0.52
    ever
    -0.52
    Ever
    -0.45
    ransition
    -0.45
    gpr
    -0.43
    fortawesome
    -0.43
    bergh
    -0.42
     gọn
    -0.42
    bürger
    -0.42
    格
    -0.42
    POSITIVE LOGITS
     تكبرها
    0.81
    migrationBuilder
    0.74
     resourceCulture
    0.73
    aarrggbb
    0.71
    DockStyle
    0.70
     שוליים
    0.70
    WriteBarrier
    0.68
    expandindo
    0.68
    MethodManager
    0.67
    Diwedd
    0.66
    Activations Density 0.014%

    No Known Activations