© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5549
    Prev
    Next
    INDEX
    Explanations

    references to "cross" and related terms in scientific 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
    hasMoreElements
    -0.83
     igång
    -0.82
    ьаж
    -0.77
    ècie
    -0.76
    RequestParam
    -0.75
     pylint
    -0.75
    upaten
    -0.74
     Magee
    -0.74
    SBATCH
    -0.73
    
    -0.73
    POSITIVE LOGITS
     CROSS
    1.63
     Cross
    1.58
    Cross
    1.54
     crosses
    1.43
    CROSS
    1.42
    cross
    1.40
     cross
    1.37
     Crossing
    1.23
     Crossroads
    1.20
     Cros
    1.19
    Activations Density 0.082%

    No Known Activations