© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 285
    Prev
    Next
    INDEX
    Explanations

    prepositions and words close by

    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.22.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.22.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
     bonté
    -0.68
     leçon
    -0.67
     teneur
    -0.60
     jugado
    -0.59
     aprendido
    -0.57
     frontière
    -0.56
     charité
    -0.56
     comprado
    -0.55
     cambiado
    -0.55
    rzu
    -0.54
    POSITIVE LOGITS
     creation
    1.16
    การ
    1.15
     introduction
    1.13
     formation
    1.11
     removal
    1.09
     completion
    1.07
     acquisition
    1.05
     establishment
    1.02
     implementation
    1.01
     incorporation
    1.00
    Activations Density 5.951%

    No Known Activations