© 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. 3914
    Prev
    Next
    INDEX
    Explanations

    variables and their definitions in code-like structures

    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
    发表于
    -0.67
     Bourgoin
    -0.66
    izop
    -0.60
     sidan
    -0.60
     harian
    -0.60
    kloped
    -0.60
    isiä
    -0.60
    Opin
    -0.60
    背包
    -0.59
    :`
    -0.59
    POSITIVE LOGITS
    Ayy
    0.98
     Azz
    0.94
     PPS
    0.92
    pp
    0.88
    edd
    0.87
     BBB
    0.86
     NCC
    0.85
     Hatt
    0.85
     Popp
    0.85
     Hadd
    0.84
    Activations Density 1.738%

    No Known Activations