© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5450
    Prev
    Next
    INDEX
    Explanations

    references to films and cinema

    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
    lodash
    -0.62
    Vrij
    -0.62
    aceae
    -0.57
    enge
    -0.56
     Cabe
    -0.56
    ++++++++++++++++
    -0.56
     Rache
    -0.56
    vės
    -0.56
     Uz
    -0.55
     Anato
    -0.55
    POSITIVE LOGITS
     films
    1.65
     FILM
    1.60
     FILMS
    1.54
     Film
    1.53
     film
    1.48
     Films
    1.48
    FILM
    1.41
    Films
    1.38
    film
    1.37
    Film
    1.35
    Activations Density 0.041%

    No Known Activations