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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74355
    Prev
    Next
    INDEX
    Explanations

    scientific/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     schedule
    -0.57
     pattern
    -0.57
    Przypisy
    -0.54
     phenotype
    -0.51
    তথ্যসূত্র
    -0.50
     strategia
    -0.50
     situatie
    -0.49
     tendência
    -0.49
    ifikation
    -0.48
     attitude
    -0.48
    POSITIVE LOGITS
     chemist
    0.77
    :✨
    0.63
    chemist
    0.61
     availa
    0.59
     ext
    0.58
    lif
    0.56
    osoba
    0.56
     sever
    0.56
     stab
    0.55
     sele
    0.55
    Activations Density 0.013%

    No Known Activations