© 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. 1149
    Prev
    Next
    INDEX
    Explanations

    the word "convert" along with prepositions "to","from", and sometimes the words "the", "your", "that", "lating", or "using".

    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
     Geist
    -0.69
     InputDecoration
    -0.68
    aarrggbb
    -0.67
    providedIn
    -0.65
    Демографія
    -0.65
     يتيمه
    -0.64
    ."],
    -0.62
    czegó
    -0.61
    ogia
    -0.60
     Weh
    -0.60
    POSITIVE LOGITS
     conversion
    2.80
     convert
    2.69
     Conversion
    2.67
     converted
    2.64
     conversions
    2.64
     converting
    2.63
     converts
    2.63
     Convert
    2.47
    Conversion
    2.42
    convert
    2.41
    Activations Density 0.518%

    No Known Activations