© 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. 25730
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating abrupt changes or surprising events

    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
    ⓧ
    -0.77
     للمعارف
    -0.71
     Culver
    -0.70
     <<<<<<<<<<<<<<
    -0.67
    ritch
    -0.64
     frutto
    -0.64
    ArrowToggle
    -0.63
     câte
    -0.63
    jmniej
    -0.63
     primaire
    -0.62
    POSITIVE LOGITS
     suddenly
    1.28
     Sudden
    1.20
     Suddenly
    1.14
    Sudden
    1.13
    Suddenly
    1.09
     sudden
    1.02
    suddenly
    1.02
     SUD
    1.00
    SUD
    0.92
    sud
    0.86
    Activations Density 0.006%

    No Known Activations