© 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. 22-RES-MATRYOSHKA-DC
    7. 817
    Prev
    Next
    INDEX
    Explanations

    mentions of people portraying roles, being voiced by someone, or generally being involved with a production.

    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
    RenderAtEndOf
    -0.66
    TabIndex
    -0.54
    humidité
    -0.54
    󠁢
    -0.54
    transQ
    -0.52
    estand
    -0.52
    mapp
    -0.51
    scalatest
    -0.51
    Билгалдахарш
    -0.51
     circulación
    -0.51
    POSITIVE LOGITS
     acting
    1.22
     actor
    1.13
     actors
    1.12
     roles
    1.07
     playing
    1.04
     Actors
    0.98
     Acting
    0.97
    actor
    0.96
     Actor
    0.96
    Acting
    0.94
    Activations Density 0.611%

    No Known Activations