© 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. 23721
    Prev
    Next
    INDEX
    Explanations

    references to a specific car model and related automotive terms

    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
     Branco
    -0.78
     Crisp
    -0.74
     Дата
    -0.73
    ruptcy
    -0.73
    וז
    -0.73
    Christy
    -0.73
     Crum
    -0.72
    />";
    -0.72
     pinulongan
    -0.71
     Zon
    -0.71
    POSITIVE LOGITS
     cam
    1.44
     CAM
    1.35
     cams
    1.35
     Cam
    1.34
    Cam
    1.33
    CAM
    1.28
    cam
    1.22
     Camden
    1.13
    cams
    1.05
     Camilo
    0.99
    Activations Density 0.010%

    No Known Activations