© 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. 3-RES-MATRYOSHKA-DC
    7. 1932
    Prev
    Next
    INDEX
    Explanations

    the word "weight" possibly followed by a description of how it has changed

    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
     OMITBAD
    -0.69
     snippetHide
    -0.69
     nahilalakip
    -0.66
     cellpadding
    -0.65
    Personendaten
    -0.62
     Crot
    -0.61
    :✨
    -0.61
     Mih
    -0.60
     Niel
    -0.60
    FontOfSize
    -0.59
    POSITIVE LOGITS
     weight
    3.47
    weight
    3.19
     Weight
    3.11
    Weight
    3.03
     weights
    3.03
     WEIGHT
    3.02
    WEIGHT
    2.89
    weights
    2.69
     Weights
    2.66
     weigh
    2.63
    Activations Density 0.229%

    No Known Activations