© 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. 17779
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions or states related to identity and obligations

    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
    rogens
    -0.63
    heta
    -0.55
     quæ
    -0.54
    ugd
    -0.52
    })}\
    -0.52
    pse
    -0.50
    tainer
    -0.50
    げて
    -0.48
    комиться
    -0.48
    \|\
    -0.48
    POSITIVE LOGITS
     Wikimedijinoj
    0.82
    mybatisplus
    0.72
    kháu
    0.71
    DeleteBehavior
    0.69
    Становништво
    0.68
    FormTagHelper
    0.66
    iastes
    0.66
    didSet
    0.65
    GeneratedCode
    0.65
    Tikang
    0.64
    Activations Density 0.005%

    No Known Activations