© 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. 22-RES-MATRYOSHKA-DC
    7. 1583
    Prev
    Next
    INDEX
    Explanations

    references to Facebook advertising

    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.22.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.22.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
    UnitTesting
    -0.66
    ValueStyle
    -0.63
     AssemblyVersion
    -0.61
    Personendaten
    -0.59
     باخ
    -0.56
    lês
    -0.56
    خصة
    -0.55
    ChildScrollView
    -0.55
    Koordinaten
    -0.54
    uzzy
    -0.54
    POSITIVE LOGITS
     Facebook
    1.75
     Twitter
    1.63
    Facebook
    1.54
     social
    1.52
     Instagram
    1.46
    Twitter
    1.39
     facebook
    1.36
     twitter
    1.30
     FACEBOOK
    1.27
     tweeting
    1.26
    Activations Density 1.102%

    No Known Activations