© 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. 14276
    Prev
    Next
    INDEX
    Explanations

    repeated commas in 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
     Legge
    -0.49
    contentPadding
    -0.49
     noqa
    -0.47
    往
    -0.44
    rsiniz
    -0.44
    optString
    -0.43
     laad
    -0.42
     fiducia
    -0.41
    fsch
    -0.40
    out
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    1.07
    rungsseite
    0.92
    AddTagHelper
    0.90
    UnsafeEnabled
    0.87
    ✨:
    0.84
    RTSC
    0.80
    awtextra
    0.78
    ResumeLayout
    0.78
    webElementXpaths
    0.75
    Autoritní
    0.75
    Activations Density 0.008%

    No Known Activations