© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    numerical values and percentages in the context of data analysis

    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
    <bos>
    -0.46
    olute
    -0.42
    le
    -0.41
    Kirchen
    -0.40
    łbym
    -0.40
     tr
    -0.40
     trat
    -0.38
     study
    -0.37
     Panamá
    -0.36
    …
    -0.36
    POSITIVE LOGITS
    存于互联网档案馆
    0.85
     CreateTagHelper
    0.80
    enumii
    0.75
    enumi
    0.75
    EndInit
    0.73
     незавершена
    0.73
     estekak
    0.71
    endpush
    0.70
     StatefulWidget
    0.68
    fony
    0.67
    Activations Density 0.215%

    No Known Activations