© 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. 674
    Prev
    Next
    INDEX
    Explanations

    the word "water" and closely related terms

    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
    Parcelize
    -0.73
     '*':
    -0.68
     Mace
    -0.65
    ModelSerializer
    -0.65
     '-':
    -0.64
     Guanajuato
    -0.64
    ModelForm
    -0.63
     OFDb
    -0.63
     Vecchio
    -0.63
    >");
    -0.63
    POSITIVE LOGITS
     water
    3.20
     Water
    3.02
    Water
    3.00
    water
    2.89
     WATER
    2.75
    WATER
    2.69
     waters
    2.23
     Wasser
    2.03
     água
    2.03
    waters
    2.02
    Activations Density 0.137%

    No Known Activations