© 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. 72389
    Prev
    Next
    INDEX
    Explanations

    Past tense verbs

    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
     الحره
    -0.51
     Preferencias
    -0.45
    macher
    -0.45
    #
    -0.43
    disha
    -0.41
    AndEndTag
    -0.41
    vi
    -0.41
    WAII
    -0.40
    amat
    -0.40
    Lima
    -0.40
    POSITIVE LOGITS
     brought
    0.86
     led
    0.84
     sent
    0.80
    brought
    0.77
     Brought
    0.75
     compelled
    0.74
    Brought
    0.74
     prompted
    0.73
     rendered
    0.71
     necessitated
    0.71
    Activations Density 0.000%

    No Known Activations