© 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. 1544
    Prev
    Next
    INDEX
    Explanations

    the word "cross" and words that start with "cross-"

    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
    Negative Logits
    
    -0.59
    PhysRevD
    -0.54
    '][$
    -0.51
     estimé
    -0.51
     ProgressDialog
    -0.50
    upaten
    -0.49
    callee
    -0.49
    execSQL
    -0.49
    heria
    -0.49
    Touchable
    -0.48
    POSITIVE LOGITS
     CROSS
    1.58
     cross
    1.48
    Cross
    1.46
     Cross
    1.45
    CROSS
    1.39
    cross
    1.38
     crosses
    1.27
     cros
    1.26
    crossed
    1.14
     crossed
    1.13
    Activations Density 0.111%

    No Known Activations