© 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. 28283
    Prev
    Next
    INDEX
    Explanations

    references to the "Scott Report" and related entities

    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
    Grimm
    -0.69
     Aniston
    -0.69
    bung
    -0.67
    SwingConstants
    -0.66
     mecánico
    -0.66
    IBinder
    -0.66
     mecán
    -0.65
    潟
    -0.65
    most
    -0.64
     Parra
    -0.64
    POSITIVE LOGITS
     LC
    1.26
    LC
    0.96
     Hawkins
    0.96
    complexType
    0.94
     Scott
    0.91
    Tikang
    0.89
    cheiben
    0.87
     Karp
    0.85
     DEAN
    0.85
     Cardoso
    0.82
    Activations Density 0.036%

    No Known Activations