© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    phrases that express legal arguments and courtroom proceedings

    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
     Infórmanos
    -0.60
     JpaRepository
    -0.60
    featureID
    -0.54
     Италијани
    -0.53
    jspb
    -0.53
     simplified
    -0.52
    AutoScaleMode
    -0.52
     تضيفلها
    -0.52
     thinned
    -0.51
    sizeCache
    -0.50
    POSITIVE LOGITS
    retain
    0.67
    enumi
    0.66
     retain
    0.65
    avía
    0.61
     persist
    0.59
     continuity
    0.57
     retained
    0.57
     obstin
    0.56
     insist
    0.55
     continuance
    0.55
    Activations Density 1.235%

    No Known Activations