© 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. 5156
    Prev
    Next
    INDEX
    Explanations

    references to frames and their properties in a technical context

    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
     Ahh
    -0.82
     noct
    -0.80
     Adkins
    -0.80
     getCity
    -0.78
     Spies
    -0.78
     Sewell
    -0.77
     OnInit
    -0.76
     Noct
    -0.75
    Mozart
    -0.75
     écout
    -0.75
    POSITIVE LOGITS
     frames
    1.86
     Frames
    1.80
    Frames
    1.70
     Frame
    1.69
     FRAME
    1.66
    frames
    1.65
    FRAME
    1.60
    Frame
    1.58
     frame
    1.57
    frame
    1.54
    Activations Density 0.062%

    No Known Activations