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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13572
    Prev
    Next
    INDEX
    Explanations

    references to specific types of disposable items, particularly balloons

    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
    GraphicsUnit
    -0.67
     preocupes
    -0.67
    Vidite
    -0.64
    Personendaten
    -0.56
    hm
    -0.55
    WithMany
    -0.54
    amse
    -0.53
     kirim
    -0.52
    ristown
    -0.52
    Gambas
    -0.52
    POSITIVE LOGITS
     balloon
    1.41
    yt
    1.38
     Balloon
    1.21
    balloon
    1.08
     balloons
    1.04
    YT
    0.96
    Balloon
    0.96
     ballo
    0.93
     ballon
    0.84
     Balloons
    0.77
    Activations Density 0.007%

    No Known Activations