© 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. 26065
    Prev
    Next
    INDEX
    Explanations

    positive and descriptive qualities, particularly highlighting the enjoyable or impactful aspects of experiences or entities

    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
    cete
    -0.53
     but
    -0.50
    уго
    -0.47
    пля
    -0.47
     :
    -0.47
    :
    -0.45
     confi
    -0.45
    :['
    -0.43
     b
    -0.42
     s
    -0.41
    POSITIVE LOGITS
     greateſt
    0.91
    AnimationsModule
    0.89
    AddTagHelper
    0.88
     NSCoder
    0.86
     itſelf
    0.85
     sequels
    0.79
     Rajah
    0.79
     Daven
    0.78
    posedge
    0.77
     themſelves
    0.77
    Activations Density 0.055%

    No Known Activations