© 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. 3780
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting

    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
     embo
    -0.66
     שוליים
    -0.63
    
    -0.58
    дент
    -0.55
     ViewGroup
    -0.52
     inst
    -0.50
     RequestMethod
    -0.50
     Insulin
    -0.50
     vra
    -0.49
    inst
    -0.49
    POSITIVE LOGITS
     насељу
    0.78
    NewUrlParser
    0.74
    XmlAccessType
    0.71
    وفاته
    0.65
    افظة
    0.64
    aktery
    0.62
    ГЛА
    0.61
     chung
    0.60
    apimachinery
    0.60
     rajut
    0.60
    Activations Density 0.052%

    No Known Activations