© 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. 18-RES-MATRYOSHKA-DC
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    the word "line" or "linear" appearing in an otherwise neutral context

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    FXML
    -0.62
    ={({
    -0.59
    SPONSORED
    -0.57
    batore
    -0.56
     estekak
    -0.56
    SerializeField
    -0.56
    BeginContext
    -0.55
     Ngb
    -0.55
    istocene
    -0.54
    ات
    -0.54
    POSITIVE LOGITS
     LINE
    1.11
     Line
    1.11
     Lines
    1.06
     lines
    1.02
    Lines
    0.97
     line
    0.96
     LINES
    0.95
    Line
    0.95
     Linea
    0.90
    lines
    0.85
    Activations Density 0.392%

    No Known Activations