© 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. 0-CLT-HP
    7. 93866
    Prev
    Next
    INDEX
    Explanations

    tips

    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
     tips
    -2.55
     Tips
    -1.64
    tips
    -1.60
    Tips
    -1.52
     tip
    -1.47
     TIPS
    -1.28
     Tip
    -1.16
     Tipps
    -1.14
     dicas
    -1.10
    tipped
    -1.09
    POSITIVE LOGITS
    y
    0.79
     for
    0.70
    er
    0.68
    es
    0.63
     to
    0.56
     and
    0.54
    .
    0.54
    r
    0.52
     on
    0.51
     around
    0.50
    Activations Density 0.020%

    No Known Activations