© 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. 26608
    Prev
    Next
    INDEX
    Explanations

    terms related to childhood and factors affecting children's development

    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
    sizeCache
    -0.58
    stylers
    -0.51
     deleted
    -0.49
    useEffect
    -0.45
    集中
    -0.44
    isolated
    -0.44
    protoimpl
    -0.43
    Isolated
    -0.43
     believe
    -0.43
     local
    -0.42
    POSITIVE LOGITS
     مرئيه
    0.71
    NewUrlParser
    0.71
    
    0.64
     Picchu
    0.63
     biographer
    0.62
    GraphicsUnit
    0.61
     Arsen
    0.60
    ]^{\
    0.59
     courtroom
    0.58
     OMIT
    0.58
    Activations Density 0.113%

    No Known Activations