© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1344
    Prev
    Next
    INDEX
    Explanations

    uses of the words "adjust", "adjusted", and "adjustment", especially in the context of statistical analysis.

    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
     betweenstory
    -0.76
    alleria
    -0.71
     Proliferation
    -0.65
     lørdag
    -0.65
     ProtoMessage
    -0.65
     nucleation
    -0.65
     Propag
    -0.64
     autorytatywna
    -0.64
     rhiz
    -0.64
     Yaman
    -0.64
    POSITIVE LOGITS
     adjustment
    2.88
     Adjustment
    2.78
     adjusted
    2.75
     adjust
    2.72
     adjusting
    2.66
     Adjust
    2.63
     ADJUST
    2.59
    Adjust
    2.58
     adjusts
    2.56
     adjustments
    2.55
    Activations Density 0.171%

    No Known Activations