© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16247
    Prev
    Next
    INDEX
    Explanations

    sign

    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
    Negative Logits
     signs
    -0.62
     signes
    -0.59
     sign
    -0.58
    Sign
    -0.55
    sign
    -0.54
     <=",
    -0.54
    StructEnd
    -0.53
     signing
    -0.49
     segno
    -0.49
    signs
    -0.49
    POSITIVE LOGITS
    IntoConstraints
    0.70
    exitRule
    0.66
    hematical
    0.61
     NSS
    0.60
    ynthia
    0.57
    pirable
    0.57
     snee
    0.56
    heiser
    0.56
    clusal
    0.56
    NegativeButton
    0.55
    Activations Density 0.013%

    No Known Activations