© 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. 15089
    Prev
    Next
    INDEX
    Explanations

    neglect

    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
     neglected
    -1.80
     neglect
    -1.53
    glected
    -1.41
     Neglect
    -1.30
     neglecting
    -1.25
     néglig
    -0.69
     ignored
    -0.68
     NEG
    -0.67
    "):
    -0.59
     negligence
    -0.59
    POSITIVE LOGITS
    ToScroll
    0.61
    umumkan
    0.59
     to
    0.54
    yarnpkg
    0.54
     doInBackground
    0.52
    cloudflare
    0.52
    EDEFAULT
    0.51
    uality
    0.50
    opardy
    0.50
    jadinya
    0.50
    Activations Density 0.006%

    No Known Activations