© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5516
    Prev
    Next
    INDEX
    Explanations

    period

    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
    however
    -0.79
    AddTagHelper
    -0.73
    latego
    -0.69
     however
    -0.67
     hivyo
    -0.65
    Поэтому
    -0.64
     архивлан
    -0.63
     additionally
    -0.63
    ALSO
    -0.63
    therefore
    -0.63
    POSITIVE LOGITS
    pdf
    0.46
    docx
    0.45
     This
    0.45
    png
    0.45
    umumkan
    0.43
     boî
    0.43
     –
    0.42
    jpg
    0.42
    lıyor
    0.42
    formKey
    0.41
    Activations Density 0.000%

    No Known Activations