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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8659
    Prev
    Next
    INDEX
    Explanations

    Spanish question words and their usage

    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
     Sequo
    -0.72
    klere
    -0.72
    ležité
    -0.71
    vamente
    -0.70
     referrerpolicy
    -0.68
    UIManager
    -0.68
    iliary
    -0.67
    PreInfinity
    -0.67
     Burgos
    -0.66
     saites
    -0.66
    POSITIVE LOGITS
    ¿
    1.41
     ¿
    1.36
     "¿
    1.15
    "¿
    1.10
    -¿
    0.96
     “¿
    0.91
    __':
    0.78
    __":
    0.77
    iquest
    0.76
    serviceWorker
    0.73
    Activations Density 0.000%

    No Known Activations