© 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. 28310
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes and variations in data or conditions

    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
     betweenstory
    -1.02
     changing
    -0.81
     changer
    -0.80
     changed
    -0.78
    changing
    -0.75
     change
    -0.74
     Changing
    -0.74
    CHANGED
    -0.73
     Changer
    -0.73
    laterra
    -0.72
    POSITIVE LOGITS
    UrlResolution
    0.66
     dipin
    0.63
    رشف
    0.62
     nmax
    0.61
     mattino
    0.61
     RISE
    0.60
     raiſ
    0.60
     fadeIn
    0.60
     crdi
    0.58
     obé
    0.58
    Activations Density 0.032%

    No Known Activations