© 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. 5265
    Prev
    Next
    INDEX
    Explanations

    COPYRIGHT

    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
     don
    -0.53
     edition
    -0.50
    jspx
    -0.49
    tilo
    -0.47
     do
    -0.47
    Ad
    -0.47
     Ad
    -0.47
    ">—
    -0.46
    DON
    -0.46
    som
    -0.45
    POSITIVE LOGITS
    ########.
    0.82
    WriteTagHelper
    0.68
    AccessorTable
    0.66
    PerformLayout
    0.62
    ed
    0.60
    ensement
    0.59
     provinciale
    0.55
    ED
    0.54
     мәкал
    0.54
     transfieras
    0.53
    Activations Density 0.004%

    No Known Activations