© 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. 0-RES-MATRYOSHKA-DC
    7. 11899
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "rewrite" in various contexts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Straw
    -0.58
     Straw
    -0.58
     Pera
    -0.58
     Sot
    -0.57
    endfor
    -0.57
     eingesch
    -0.56
     hypothalamus
    -0.56
     labour
    -0.56
    //}
    -0.56
     Beren
    -0.56
    POSITIVE LOGITS
    Rewrite
    1.59
    rewrite
    1.32
    kir
    1.21
     Rewrite
    1.19
    Kir
    1.01
     Kir
    0.94
    pak
    0.92
     rewrite
    0.84
     Pak
    0.81
     pak
    0.77
    Activations Density 0.007%

    No Known Activations