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. 9-RES-MATRYOSHKA-DC
    4. 16546
    Prev
    Next
    INDEX
    Explanations

    phrases with `should`,`must` or `have to` (expressing opinions, obligation, or planning)

    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
     nawr
    -0.74
    তথ্যসূত্র
    -0.72
     gynhyrchwyd
    -0.69
     betweenstory
    -0.69
    MigrationBuilder
    -0.68
    SharedDtor
    -0.66
    RetentionPolicy
    -0.64
     препратки
    -0.62
    kään
    -0.62
     invitamos
    -0.60
    POSITIVE LOGITS
    AndSet
    0.67
    badlogic
    0.58
     Meilleures
    0.58
     consulté
    0.57
    :][
    0.56
    Portale
    0.55
    vismo
    0.54
    typer
    0.54
    melse
    0.54
     "/")
    0.54
    Activations Density 0.031%

    No Known Activations