© 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. 24-RES-MATRYOSHKA-DC
    7. 302
    Prev
    Next
    INDEX
    Explanations

    Dollar amounts and/or references to paying for real estate

    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.24.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.24.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
     pinulongan
    -0.70
     فريبيس
    -0.69
     يتيمه
    -0.63
    ArgsConstructor
    -0.62
    
    -0.56
    vacy
    -0.56
    âmica
    -0.55
     CURIAM
    -0.52
    AllowUser
    -0.52
    igkeit
    -0.52
    POSITIVE LOGITS
     cash
    1.16
     dollars
    1.12
     money
    1.10
     payments
    1.05
     $
    1.05
     amounts
    1.00
     amount
    0.98
     ($
    0.97
     $\$
    0.96
     payment
    0.96
    Activations Density 3.195%

    No Known Activations