© 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. 95384
    Prev
    Next
    INDEX
    Explanations

    approval

    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
     approval
    -1.31
     approve
    -1.31
     approving
    -1.25
     Approval
    -1.23
     APPROVAL
    -1.13
     approved
    -1.11
    approval
    -1.11
     approves
    -1.05
     approvals
    -1.05
     Approved
    -1.04
    POSITIVE LOGITS
     a
    0.57
    бки
    0.55
     the
    0.53
     “
    0.50
     an
    0.48
     of
    0.48
     base
    0.48
     ο
    0.48
     for
    0.47
     multiple
    0.47
    Activations Density 0.198%

    No Known Activations