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. 16516
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    KURZBESCHREIBUNG
    -0.66
     المعيارى
    -0.65
    URLException
    -0.60
    /*
    -0.59
     Viitattu
    -0.57
    ǔ
    -0.57
    Sag
    -0.56
     للاسماء
    -0.56
    يكب
    -0.55
    Referencies
    -0.55
    POSITIVE LOGITS
    MigrationBuilder
    0.61
    
    0.56
    BindingResult
    0.49
    WriteLiteral
    0.48
     toek
    0.46
     posteriores
    0.45
     Heinemann
    0.45
     altre
    0.44
    beiten
    0.44
     armado
    0.44
    Activations Density 0.044%

    No Known Activations