Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30890
    Prev
    Next
    INDEX
    Explanations

    common words that are near the word "that"

    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
     CreateTagHelper
    -0.85
     חיצוניים
    -0.85
     ब्रेकडाउन
    -0.84
     AssemblyProduct
    -0.81
     Administrativna
    -0.79
    RegistryLite
    -0.74
     विश्वसनीयता
    -0.70
    
    -0.69
    ########.
    -0.69
    vician
    -0.69
    POSITIVE LOGITS
    期
    0.46
     mak
    0.44
     state
    0.43
     another
    0.43
     king
    0.41
     HELL
    0.40
     leading
    0.39
    BorderSize
    0.39
    protoc
    0.39
    dotenv
    0.38
    Activations Density 1.338%

    No Known Activations