© 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. 25992
    Prev
    Next
    INDEX
    Explanations

    the presence of slashes, which typically denote fractions or divisions in numerical or academic contexts

    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
    bin
    -0.54
     SUDOC
    -0.54
     event
    -0.51
     agent
    -0.50
     luk
    -0.48
    └──
    -0.48
    nande
    -0.48
    pac
    -0.47
    İN
    -0.47
     ball
    -0.46
    POSITIVE LOGITS
    UnusedPrivate
    0.79
    Hentet
    0.75
     مشين
    0.73
    KommentareTeilen
    0.70
     propOrder
    0.70
    AndEndTag
    0.68
    setVerticalGroup
    0.67
    StructEnd
    0.67
     AppCompatTheme
    0.66
    ToBounds
    0.66
    Activations Density 0.001%

    No Known Activations