© 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. 8480
    Prev
    Next
    INDEX
    Explanations

    references to visual effects and cinematography in films

    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
    ValueStyle
    -0.59
     aceptas
    -0.56
    fromnode
    -0.55
     Habana
    -0.54
    lingo
    -0.53
     Confucius
    -0.53
    ScopeManager
    -0.52
    Clik
    -0.50
     hearth
    -0.49
    GEBRA
    -0.48
    POSITIVE LOGITS
     كومونز
    0.65
    CodeAttribute
    0.54
    rrggbb
    0.54
    providedIn
    0.50
     Dey
    0.50
    mendous
    0.50
     cinematogra
    0.50
    씬
    0.50
    enery
    0.49
    >>()
    0.49
    Activations Density 0.056%

    No Known Activations