© 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. 15641
    Prev
    Next
    INDEX
    Explanations

    terms related to unusual or peculiar experiences

    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
    ViewFeatures
    -0.95
     Trafalgar
    -0.86
    jsonwebtoken
    -0.84
     Roskov
    -0.83
    θρώ
    -0.82
     propOrder
    -0.82
     nakalista
    -0.77
     disambiguazione
    -0.76
     Audiodateien
    -0.73
    XmlAccessorType
    -0.72
    POSITIVE LOGITS
     Weird
    0.75
    Weird
    0.71
     weird
    0.70
    weird
    0.68
    瘩
    0.66
     tiet
    0.63
    izarro
    0.56
    kward
    0.55
     wierd
    0.55
    misc
    0.54
    Activations Density 0.008%

    No Known Activations