© 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. 72967
    Prev
    Next
    INDEX
    Explanations

    Incomplete phrases

    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
     to
    -0.64
     irrigation
    -0.56
     बिना
    -0.53
     dredging
    -0.52
    두
    -0.50
    ibase
    -0.50
     sediment
    -0.50
     Kelle
    -0.50
    liebte
    -0.49
    ftagPool
    -0.49
    POSITIVE LOGITS
     CanadaChoose
    0.74
    ViewFeatures
    0.71
    nloa
    0.61
     Савезне
    0.59
     gezet
    0.57
    tagHelperRunner
    0.56
    MENAFN
    0.53
     jangka
    0.51
     hänen
    0.51
    lève
    0.50
    Activations Density 0.008%

    No Known Activations