© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5803
    Prev
    Next
    INDEX
    Explanations

    expressions of willingness, encouragement, and emotional resilience

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -1.23
    Obrázky
    -1.02
     disambiguazione
    -1.01
     كومونز
    -1.00
    SpringRunner
    -0.97
     AssemblyCompany
    -0.95
     jLabel
    -0.93
    GEBURTSDATUM
    -0.93
     &___
    -0.92
    CONSIN
    -0.92
    POSITIVE LOGITS
     to
    1.42
    to
    0.63
    ที่จะ
    0.63
     чтобы
    0.63
     attempt
    0.60
     able
    0.56
     щоб
    0.52
     să
    0.52
     need
    0.49
    INV
    0.49
    Activations Density 0.481%

    No Known Activations