© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16070
    Prev
    Next
    INDEX
    Explanations

    dots or breaks in the text, signifying the end of sentences

    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
    
    -0.83
    "}")
    -0.73
    _;
    
    -0.72
    }")
    
    -0.69
     ब्रेकडाउन
    -0.69
    Gambas
    -0.69
    /−
    -0.69
    PhysRev
    -0.68
     ['$
    -0.67
    _))
    -0.67
    POSITIVE LOGITS
     Peker
    0.57
     aw
    0.50
    رحلة
    0.49
    PostExecute
    0.48
    BeforeMethod
    0.47
     StatelessWidget
    0.47
     ferien
    0.47
     dita
    0.46
     rather
    0.46
    +#+
    0.45
    Activations Density 0.000%

    No Known Activations