© 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. 15476
    Prev
    Next
    INDEX
    Explanations

    numbers and their relationships in a context related to actions or decisions

    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
     Rie
    -0.63
    teis
    -0.57
     Lap
    -0.56
     της
    -0.53
     знаешь
    -0.53
     a
    -0.52
     coper
    -0.51
    usza
    -0.51
     áng
    -0.50
     Basi
    -0.50
    POSITIVE LOGITS
     myſelf
    1.17
     Reſ
    0.98
     uſe
    0.95
     themſelves
    0.94
     للمعارف
    0.93
     purpoſe
    0.92
     himſelf
    0.91
     cauſe
    0.91
     againſt
    0.90
     fhew
    0.89
    Activations Density 0.154%

    No Known Activations