© 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. 1-CLT-HP
    7. 14815
    Prev
    Next
    INDEX
    Explanations

    uses the word "with"

    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
    GEBURTSDATUM
    -0.77
     CreateTagHelper
    -0.61
    AutoScaleMode
    -0.60
    principalColumn
    -0.57
     تضيفلها
    -0.54
    httphttps
    -0.53
    qtype
    -0.52
    StackNavigator
    -0.51
    Erreferentziak
    -0.50
     récentes
    -0.50
    POSITIVE LOGITS
     catching
    0.59
     soundly
    0.59
     Moi
    0.59
     ratify
    0.58
    orosi
    0.57
    DetailActivity
    0.57
     between
    0.56
     helping
    0.55
     Them
    0.55
    edero
    0.55
    Activations Density 0.257%

    No Known Activations