© 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. 5-CLT-HP
    7. 6009
    Prev
    Next
    INDEX
    Explanations

    second instance

    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
     continúas
    -0.65
     кӀ
    -0.60
    Демографія
    -0.58
    setVerticalGroup
    -0.56
    Composable
    -0.54
     dAtA
    -0.54
    tocin
    -0.50
    Populations
    -0.50
    IBOutlet
    -0.50
    contentLoaded
    -0.47
    POSITIVE LOGITS
    kegaard
    0.55
     QWidget
    0.53
    ceq
    0.53
     ")"
    0.52
     JOptionPane
    0.52
     IOError
    0.52
    ubere
    0.51
    dus
    0.51
    oxo
    0.51
    </tfoot>
    0.51
    Activations Density 0.010%

    No Known Activations