© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16667
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or expressions, particularly those indicating norms or operations involving vector spaces

    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
     Trondheim
    -0.75
     nicio
    -0.72
     חיצוניים
    -0.71
    ormais
    -0.70
     franceses
    -0.68
     nė
    -0.67
     mardi
    -0.66
     roost
    -0.65
     Carlsbad
    -0.65
     stringBy
    -0.65
    POSITIVE LOGITS
     Vert
    1.05
    Vert
    1.03
    vertx
    1.02
    vert
    0.96
     vert
    0.84
    %;">
    0.79
    '])
    
    0.74
    VERT
    0.73
    '>
    
    0.73
    Verte
    0.71
    Activations Density 0.014%

    No Known Activations