© 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. 27179
    Prev
    Next
    INDEX
    Explanations

    references to juveniles and juvenile-related issues

    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
    Negative Logits
    FormTagHelper
    -0.89
    BagConstraints
    -0.80
    ScopeManager
    -0.79
     estimés
    -0.79
    :+:
    -0.75
    డ్
    -0.75
     Mana
    -0.75
     disambiguazione
    -0.74
     للاسماء
    -0.73
     autorytatywna
    -0.71
    POSITIVE LOGITS
     Juven
    1.03
     juvenile
    1.00
     Juvenile
    0.99
    UVEN
    0.92
    juven
    0.91
     juven
    0.90
    Juvenile
    0.85
     juveniles
    0.82
     juvenil
    0.80
    Juven
    0.76
    Activations Density 0.001%

    No Known Activations