© 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. 11111
    Prev
    Next
    INDEX
    Explanations

    file paths or directory structures in the text

    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
     Blender
    -0.63
    %")
    -0.61
     Salom
    -0.61
    addClass
    -0.59
    >")
    -0.58
    ?」
    -0.58
     Hic
    -0.57
     Paloma
    -0.57
    ilar
    -0.57
    InitStruct
    -0.57
    POSITIVE LOGITS
     /
    0.89
    (['/
    0.84
     Mayfield
    0.78
     Gough
    0.77
    :/
    0.75
    \/
    0.73
     Gruber
    0.72
    =/
    0.71
    karni
    0.71
    Collegamenti
    0.69
    Activations Density 0.025%

    No Known Activations