© 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. 8403
    Prev
    Next
    INDEX
    Explanations

    topics related to the concept of "for the sake of" in discussions or arguments

    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
     vi
    -0.57
     O
    -0.54
    vi
    -0.53
    tabular
    -0.53
     top
    -0.52
     v
    -0.51
     unit
    -0.50
     VI
    -0.50
    tr
    -0.50
     tangga
    -0.49
    POSITIVE LOGITS
     Sake
    1.22
     sake
    1.13
     Purposes
    0.86
     EconPapers
    0.84
     Purpose
    0.84
    RenderAtEndOf
    0.80
     purposes
    0.79
     InputDecoration
    0.79
    gatsby
    0.78
    purposes
    0.78
    Activations Density 0.010%

    No Known Activations