© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30496
    Prev
    Next
    INDEX
    Explanations

    patterns of underscores or lines representing spaces or formatting elements

    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
    /*
    -0.71
     hư
    -0.61
     Normdatei
    -0.60
    Gön
    -0.59
    .*")]
    -0.58
    parsedMessage
    -0.55
     ceci
    -0.54
     getF
    -0.54
    WithIOException
    -0.54
    AndroidJUnit
    -0.53
    POSITIVE LOGITS
    XmlAccessorType
    0.77
    makeConstraints
    0.74
    Décès
    0.67
     propOrder
    0.66
    مصادر
    0.65
    
    0.65
     Shakira
    0.60
     decoradas
    0.57
     disambiguazione
    0.57
     Reverso
    0.56
    Activations Density 0.002%

    No Known Activations