© 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. 13451
    Prev
    Next
    INDEX
    Explanations

    recurring patterns or structures related to the word "form."

    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
    InputBorder
    -1.00
    StructEnd
    -0.98
     Forming
    -0.94
     Formed
    -0.93
    forming
    -0.91
     forming
    -0.89
    InjectAttribute
    -0.83
     formation
    -0.81
    formation
    -0.81
     Formation
    -0.80
    POSITIVE LOGITS
    makeConstraints
    0.53
    ждународ
    0.50
    Пото
    0.50
     tricks
    0.47
     turned
    0.46
     kuri
    0.46
    bede
    0.46
     help
    0.46
    rop
    0.46
    iParam
    0.46
    Activations Density 0.009%

    No Known Activations