© 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. 16206
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables in scientific 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
    StoryboardSegue
    -0.77
    省市镇
    -0.60
     [*]
    -0.60
    ModelBuilder
    -0.57
    newtheorem
    -0.57
    aarrggbb
    -0.57
    icordia
    -0.56
     houſe
    -0.55
    AutoScaleMode
    -0.55
    stylesheet
    -0.54
    POSITIVE LOGITS
    ("")]
    0.63
    WIRE
    0.55
     rootReducer
    0.54
    
    0.54
     发表于
    0.52
    ]--;
    0.52
     zug
    0.51
    достатки
    0.51
    ésus
    0.50
    unhofer
    0.50
    Activations Density 0.008%

    No Known Activations