© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 1298
    Prev
    Next
    INDEX
    Explanations

    punctuation marks such as commas, hyphens, parentheses, em dashes, and ellipses

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    esez
    -0.74
     surla
    -0.70
    WaitGroup
    -0.61
     InputDecoration
    -0.61
    DebuggerStep
    -0.60
    SuccessListener
    -0.58
    reathe
    -0.57
    PendingIntent
    -0.57
     كومونز
    -0.55
     jadx
    -0.55
    POSITIVE LOGITS
    "]));
    0.76
    '])
    
    0.74
    '])){
    
    0.68
    "}")
    0.68
    "]))
    0.67
    ']))
    0.66
    "]).
    0.66
    ']))
    
    0.65
    ″]
    0.64
    enderror
    0.64
    Activations Density 0.843%

    No Known Activations