© 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. 5-CLT-HP
    7. 4721
    Prev
    Next
    INDEX
    Explanations

    such

    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
     as
    -0.53
     so
    -0.53
     on
    -0.49
     in
    -0.47
     (
    -0.46
    '
    -0.45
     like
    -0.43
     for
    -0.43
    for
    -0.41
     too
    -0.40
    POSITIVE LOGITS
     مشين
    0.96
     purpoſe
    0.93
     Monfieur
    0.91
    ^(@)
    0.88
    AntiForgeryToken
    0.87
     فريبيس
    0.86
     tartalomajánló
    0.86
    ſelves
    0.86
    bewerken
    0.86
     pleaſure
    0.85
    Activations Density 0.004%

    No Known Activations