© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 944
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · 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
     تضيفلها
    -0.60
     names
    -0.42
    name
    -0.40
     nome
    -0.40
     ProtoMessage
    -0.37
    MemoryWarning
    -0.36
    ूह
    -0.36
     named
    -0.35
     name
    -0.35
    ">//
    -0.35
    POSITIVE LOGITS
     виправивши
    0.80
     pleaſure
    0.78
     Theſe
    0.77
     Majefty
    0.77
     purpoſe
    0.75
     فريبيس
    0.74
     greateſt
    0.72
    IUrlHelper
    0.71
    ₁(
    0.71
     Shakspeare
    0.71
    Activations Density 0.002%

    No Known Activations