© 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. 11299
    Prev
    Next
    INDEX
    Explanations

    equalities or equations involving numerical values

    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
     estimés
    -0.87
    ه
    -0.79
    ioutil
    -0.73
    er
    -0.72
    sidemargin
    -0.71
    ("|
    -0.71
     Aditya
    -0.71
     uParam
    -0.69
    ்ச
    -0.68
     états
    -0.67
    POSITIVE LOGITS
     = 
    1.39
     × 
    1.23
     + 
    1.08
     doubtnut
    1.06
     < 
    1.02
     Theſe
    1.01
     myſelf
    1.00
     ± 
    0.98
     whoſe
    0.97
     raiſ
    0.95
    Activations Density 0.008%

    No Known Activations