© 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. 43434
    Prev
    Next
    INDEX
    Explanations

    cers

    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
    ever
    -0.49
     utilized
    -0.49
     étab
    -0.47
     ért
    -0.47
     ovan
    -0.45
     cuales
    -0.45
    ed
    -0.45
     complètes
    -0.45
    makta
    -0.44
    out
    -0.44
    POSITIVE LOGITS
    EndInit
    0.79
     <>",
    0.75
     doInBackground
    0.72
     <<<<<<<<<<<<<<
    0.71
     Theſe
    0.71
    +#+#
    0.70
    PreferredItem
    0.69
    Carriera
    0.68
     Quar
    0.67
    !*\
    0.66
    Activations Density 0.034%

    No Known Activations