© 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. 30225
    Prev
    Next
    INDEX
    Explanations

    references to titles or headings in documents

    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
    Looper
    -0.48
    ษัท
    -0.47
    removeAttr
    -0.47
     evaluar
    -0.45
     français
    -0.45
    发表于
    -0.44
    фильм
    -0.42
     fok
    -0.42
     obce
    -0.42
     cí
    -0.42
    POSITIVE LOGITS
    +#+#
    0.72
    
    0.69
    ✭✭
    0.68
    Портал
    0.67
     utafitiHapana
    0.66
    ✨:
    0.65
     doInBackground
    0.65
    jsxFileName
    0.60
    ReusableCell
    0.60
    Revenir
    0.59
    Activations Density 0.000%

    No Known Activations