© 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. 1-CLT-HP
    7. 13698
    Prev
    Next
    INDEX
    Explanations

    Abbreviations/codes

    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
     ISNI
    -0.71
    SerializedSize
    -0.71
     autorytatywna
    -0.71
     esternos
    -0.69
    WebVitals
    -0.68
     ModelRenderer
    -0.64
    脚注の使い方
    -0.62
     Paglinawan
    -0.61
     ſtate
    -0.60
     CreateTagHelper
    -0.59
    POSITIVE LOGITS
    ental
    0.45
    enzio
    0.45
    operate
    0.44
     Pole
    0.44
    gana
    0.41
    arche
    0.41
    atom
    0.41
    uanto
    0.40
    AppendLine
    0.40
     anlay
    0.40
    Activations Density 0.022%

    No Known Activations