© 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. 20918
    Prev
    Next
    INDEX
    Explanations

    key phrases and structures in scientific or technical writing

    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
    AccessorTable
    -0.59
    "){
    -0.54
    ";
    -0.51
    "),
    -0.49
     profondità
    -0.48
     spéciaux
    -0.46
     cojín
    -0.45
     [],
    -0.44
     supporting
    -0.44
    '],
    -0.44
    POSITIVE LOGITS
    LabelTagHelper
    0.75
    AndEndTag
    0.73
    kloped
    0.69
    DockStyle
    0.67
     Kinect
    0.65
    ArgsConstructor
    0.64
     StringTokenizer
    0.63
    potranspiration
    0.63
    tanleria
    0.61
    .*")]
    0.60
    Activations Density 0.322%

    No Known Activations