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. 73883
    Prev
    Next
    INDEX
    Explanations

    Technical/programming snippets

    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
     AssemblyTitle
    -0.78
    хьтан
    -0.60
     Baillargeon
    -0.54
     defaultstate
    -0.54
    HostException
    -0.53
     ObjectParameter
    -0.52
    +:+
    -0.50
     meinte
    -0.49
    fjspx
    -0.48
    giene
    -0.48
    POSITIVE LOGITS
     EconPapers
    0.58
    ubes
    0.54
     universal
    0.54
    WireFormatLite
    0.53
     trials
    0.50
     Works
    0.49
     ein
    0.49
    ]--;
    0.48
    \}\\
    0.47
     power
    0.46
    Activations Density 0.000%

    No Known Activations