© 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. 5221
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantities

    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
     myſelf
    -0.80
    ſelf
    -0.77
     itſelf
    -0.75
     Efq
    -0.74
     purpoſe
    -0.72
     Jefus
    -0.67
     fevere
    -0.67
     ſy
    -0.66
     pleaſure
    -0.66
     himſelf
    -0.65
    POSITIVE LOGITS
    contentLoaded
    0.58
    __*/
    0.50
    RegressionTest
    0.48
    ########.
    0.48
    Datuak
    0.48
     Even
    0.48
    LError
    0.48
     typelib
    0.47
     even
    0.47
    afficheront
    0.47
    Activations Density 0.025%

    No Known Activations