© 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. 22-RES-MATRYOSHKA-DC
    7. 2528
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions

    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
     student
    -0.68
    STUDENT
    -0.57
    student
    -0.57
     studen
    -0.56
     STUDENT
    -0.54
     lockers
    -0.54
     Student
    -0.54
     locker
    -0.52
    Student
    -0.52
     dissertation
    -0.51
    POSITIVE LOGITS
     technical
    0.77
     Technical
    0.75
    technical
    0.74
     تضيفلها
    0.69
     TECHNICAL
    0.66
    Technical
    0.66
    ństw
    0.64
     teknis
    0.64
    ycznego
    0.62
    TECHNICAL
    0.61
    Activations Density 0.157%

    No Known Activations