© 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. 6-RES-MATRYOSHKA-DC
    7. 719
    Prev
    Next
    INDEX
    Explanations

    the word "scale" and words associated with it, even when surrounded by code

    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
    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
     Dempsey
    -0.66
    orescent
    -0.63
    phite
    -0.62
    Neigh
    -0.62
    otheby
    -0.62
    razit
    -0.62
    ᵎ
    -0.62
     pios
    -0.61
     bună
    -0.60
    uarts
    -0.60
    POSITIVE LOGITS
     scales
    2.33
     scale
    2.27
     Scale
    2.27
     Scales
    2.19
     SCALE
    2.17
    Scale
    2.14
    Scales
    2.09
    scale
    2.02
    scales
    2.00
    SCALE
    1.98
    Activations Density 0.230%

    No Known Activations