© 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. 12-RES-MATRYOSHKA-DC
    7. 996
    Prev
    Next
    INDEX
    Explanations

    references to text or content that is previously mentioned

    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
    FileNotFound
    -0.64
    Portail
    -0.62
    riwal
    -0.62
     CreateTagHelper
    -0.60
    SuccessListener
    -0.60
    essége
    -0.59
    entiary
    -0.58
    %")
    -0.58
    ril
    -0.57
    ywna
    -0.57
    POSITIVE LOGITS
     ABOVE
    1.62
    above
    1.60
     above
    1.59
     Above
    1.47
    ABOVE
    1.47
    Above
    1.46
    bove
    1.34
     BELOW
    1.25
     foregoing
    1.17
    below
    1.17
    Activations Density 0.231%

    No Known Activations