© 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. 28552
    Prev
    Next
    INDEX
    Explanations

    mentions of television stations and networks

    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
    otide
    -0.50
     MainAxisSize
    -0.48
     n
    -0.45
    四大
    -0.43
     para
    -0.42
    🌙
    -0.41
    FontStyle
    -0.41
    contentPadding
    -0.40
    extAlignment
    -0.40
     major
    -0.40
    POSITIVE LOGITS
     /\.
    0.92
     ainfi
    0.72
     Efq
    0.71
     quæ
    0.70
     getSystem
    0.70
     enfans
    0.69
     ſtate
    0.67
     ſta
    0.66
    хьтан
    0.66
    ientôt
    0.66
    Activations Density 0.014%

    No Known Activations