Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31478
    Prev
    Next
    INDEX
    Explanations

    similes using the words "like" or "as".

    oai_token-act-pair · gemini-2.0-flash
    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
    UserScript
    -0.82
    EndContext
    -0.81
    BeginContext
    -0.80
    SupportActionBar
    -0.73
    didSet
    -0.71
    fromnode
    -0.70
    StructEnd
    -0.69
     AssemblyProduct
    -0.68
    UrlResolution
    -0.68
    GEBURTSDATUM
    -0.68
    POSITIVE LOGITS
     like
    0.51
     a
    0.50
     Like
    0.48
    Like
    0.47
     fast
    0.45
    ผ
    0.43
    like
    0.43
    fast
    0.43
    vol
    0.42
    zan
    0.42
    Activations Density 0.042%

    No Known Activations