© 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. 3894
    Prev
    Next
    INDEX
    Explanations

    the term "prospective," indicating studies or analyses that are forward-looking or involve observation over time

    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
    balls
    -0.77
    pidou
    -0.73
    minton
    -0.70
    greja
    -0.68
     Maid
    -0.68
    enetrable
    -0.67
     الدولى
    -0.67
     DataTypes
    -0.66
     Balls
    -0.66
     Hati
    -0.66
    POSITIVE LOGITS
     Prospective
    1.16
     PROSPECT
    1.12
     prospec
    1.11
     Prospect
    1.09
     prospective
    1.05
    spective
    1.05
    Prospect
    1.04
    Perspective
    0.94
     Prospects
    0.87
     prospects
    0.83
    Activations Density 0.010%

    No Known Activations