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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1225
    Prev
    Next
    INDEX
    Explanations

    Statement continuation

    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
    chehen
    -0.54
    :
    -0.48
    .
    -0.48
    libft
    -0.48
     and
    -0.47
    뀌
    -0.45
    Able
    -0.44
     constitutes
    -0.43
    CREAT
    -0.43
    Easily
    -0.42
    POSITIVE LOGITS
    DoubleQuotes
    0.64
     AssemblyCulture
    0.62
     CreateTagHelper
    0.59
    ]='\
    0.59
    jspb
    0.59
     resourceCulture
    0.58
     **/
    0.57
    <>());
    0.57
    mbic
    0.57
    OOTDTY
    0.56
    Activations Density 0.008%

    No Known Activations