© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13958
    Prev
    Next
    INDEX
    Explanations

    references to the importance or emphasis of the word "given."

    oai_token-act-pair · gpt-4.1-nano
    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
    ագր
    -0.60
    drawSprites
    -0.54
    Према
    -0.53
    esez
    -0.53
     her
    -0.50
     another
    -0.50
    umfang
    -0.50
    WireFormatLite
    -0.49
    νονται
    -0.49
     ‘
    -0.48
    POSITIVE LOGITS
     proverbs
    0.68
     dă
    0.66
     fenô
    0.63
     chiese
    0.62
     fédé
    0.61
    lahraga
    0.61
     giver
    0.60
    Give
    0.60
     générer
    0.59
     rhetor
    0.59
    Activations Density 0.005%

    No Known Activations