© 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. 896
    Prev
    Next
    INDEX
    Explanations

    the word "add" alone or as part of a phrase.

    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
    findpost
    -1.17
     engraçadas
    -0.86
    évaluateur
    -0.85
    maketitle
    -0.84
    ::~
    -0.79
    !*\
    -0.79
     IBOutlet
    -0.78
    \{\\
    -0.76
    mazoo
    -0.76
     Roskov
    -0.75
    POSITIVE LOGITS
     add
    2.95
     Add
    2.77
    Add
    2.63
    add
    2.56
     adds
    2.56
     ADD
    2.55
     added
    2.53
     adding
    2.53
     Adding
    2.41
    ADD
    2.36
    Activations Density 0.361%

    No Known Activations