© 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. 2562
    Prev
    Next
    INDEX
    Explanations

    phrases advocating for personal responsibility and effort

    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
     tslint
    -0.82
     المعيارى
    -0.71
    terness
    -0.70
    CloseOperation
    -0.69
     TextInputType
    -0.69
    sidemargin
    -0.69
     BorderRadius
    -0.69
     itſelf
    -0.67
    `,
    -0.66
     مؤرشف
    -0.65
    POSITIVE LOGITS
    すれば
    0.72
    れば
    0.54
     megfe
    0.51
     properly
    0.50
    えば
    0.50
     suitably
    0.50
    せば
    0.48
     megfelelő
    0.46
     ajutor
    0.45
    sufficient
    0.45
    Activations Density 0.471%

    No Known Activations