© 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. 20-CLT-HP
    7. 77642
    Prev
    Next
    INDEX
    Explanations

    the present time

    np_max-act-logits · 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
     then
    -1.46
     тогда
    -1.34
     damals
    -1.28
     entonces
    -1.18
     damaligen
    -1.15
     wtedy
    -1.14
     THEN
    -1.13
     Then
    -1.09
    then
    -1.08
     alors
    -1.07
    POSITIVE LOGITS
     currently
    1.51
     today
    1.47
    currently
    1.42
     Currently
    1.40
     presently
    1.39
     current
    1.36
    Currently
    1.34
    today
    1.34
     actuellement
    1.33
    current
    1.30
    Activations Density 0.000%

    No Known Activations