© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4107
    Prev
    Next
    INDEX
    Explanations

    references to media and its various forms or types

    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
    Rang
    -0.74
     Rang
    -0.73
     pis
    -0.72
    pis
    -0.71
     Pickett
    -0.68
     Dob
    -0.67
     Eck
    -0.65
    Eck
    -0.65
    dong
    -0.64
     zag
    -0.64
    POSITIVE LOGITS
    MEDIA
    1.55
     MEDIA
    1.48
     Media
    1.43
     medias
    1.37
    Media
    1.36
     media
    1.30
    media
    1.29
    medias
    1.09
     MediaType
    1.09
     Medien
    1.07
    Activations Density 0.062%

    No Known Activations