© 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. 22-RES-MATRYOSHKA-DC
    7. 2494
    Prev
    Next
    INDEX
    Explanations

    descriptions or responses to difficult problems or situations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     szóci
    -0.62
    تقاوى
    -0.56
    Tikang
    -0.53
     ویکی‌پدیای
    -0.50
     ویکی‌پدیا
    -0.48
     mỗi
    -0.48
    tagext
    -0.47
     finnas
    -0.47
     appunto
    -0.47
    libft
    -0.46
    POSITIVE LOGITS
     prosperity
    0.79
     success
    0.78
     financial
    0.75
     fortune
    0.73
    success
    0.71
     quarrels
    0.71
     business
    0.69
     wealth
    0.68
    perity
    0.68
     enemies
    0.67
    Activations Density 0.087%

    No Known Activations