© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3897
    Prev
    Next
    INDEX
    Explanations

    references to the word "here," indicating that it detects when the text discusses or highlights a specific point or location

    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
     Paglinawan
    -0.91
    ernalia
    -0.73
     Bioaccumulative
    -0.71
    lielmo
    -0.69
    sidemargin
    -0.69
     Commencez
    -0.69
    SharedCtor
    -0.69
    发表于
    -0.65
    SBATCH
    -0.64
    niająca
    -0.64
    POSITIVE LOGITS
     Here
    1.54
    Here
    1.30
     Voici
    0.85
    Voici
    0.81
     Below
    0.77
    Heres
    0.75
     Aquí
    0.73
    Below
    0.72
     Berikut
    0.67
    Aquí
    0.66
    Activations Density 0.031%

    No Known Activations