© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45249
    Prev
    Next
    INDEX
    Explanations

    Anecdotes

    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
    <bos>
    -0.80
     itſelf
    -0.54
     Италијани
    -0.52
    marvin
    -0.50
    varargin
    -0.49
    发表于
    -0.48
    igkeit
    -0.47
     themſelves
    -0.46
    '
    -0.46
    eseorang
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.84
     autorytatywna
    0.69
    MemoryWarning
    0.63
    fence
    0.60
     ligiloj
    0.57
    force
    0.56
     newBuilder
    0.56
    timer
    0.56
    dup
    0.56
    table
    0.55
    Activations Density 0.087%

    No Known Activations