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. 31226
    Prev
    Next
    INDEX
    Explanations

    the word 'severity'

    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
     INE
    -0.76
     Himo
    -0.73
    Tamara
    -0.65
     Мексичка
    -0.65
    glBindBuffer
    -0.65
     DNI
    -0.63
    makeConstraints
    -0.60
     Nara
    -0.60
     sapiens
    -0.59
    StructEnd
    -0.59
    POSITIVE LOGITS
     Severity
    0.85
    Severity
    0.84
    severity
    0.79
    migrationBuilder
    0.75
     كومونز
    0.71
     يتيمه
    0.71
    initState
    0.69
     severity
    0.69
    iffion
    0.68
     Cleary
    0.68
    Activations Density 0.003%

    No Known Activations