© 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. 26924
    Prev
    Next
    INDEX
    Explanations

    occurrences of the underscore character

    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
    Negative Logits
    fromnode
    -0.81
    ChildScrollView
    -0.75
    )__
    -0.74
    chiede
    -0.69
    rinology
    -0.69
    ={`/
    -0.67
    мәләр
    -0.65
     astron
    -0.64
    shund
    -0.64
     gainera
    -0.63
    POSITIVE LOGITS
    tagext
    0.61
    XmlAccessType
    0.50
    jface
    0.50
     Preference
    0.47
    헌
    0.47
    ContentAlignment
    0.47
    AsUp
    0.47
    inière
    0.46
     vapeur
    0.46
    qwerty
    0.44
    Activations Density 0.000%

    No Known Activations