© 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. 32144
    Prev
    Next
    INDEX
    Explanations

    occurrences of the characters and symbols commonly used in non-English languages

    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
     Mayer
    -0.64
     Foxx
    -0.63
    gige
    -0.60
    aarrggbb
    -0.59
     Popp
    -0.58
     paper
    -0.57
    تماد
    -0.56
    paper
    -0.56
     Ate
    -0.56
    rapt
    -0.56
    POSITIVE LOGITS
    Ù
    1.00
    Ø
    0.84
     ExecuteAsync
    0.83
     Ø
    0.80
    ValueStyle
    0.80
    fml
    0.79
     Egl
    0.75
    InvalidProtocol
    0.74
    Û
    0.73
     HasFactory
    0.73
    Activations Density 0.001%

    No Known Activations