© 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. 5630
    Prev
    Next
    INDEX
    Explanations

    school

    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
     كومونز
    -0.67
    ⓧ
    -0.56
     jsPsych
    -0.55
    aktus
    -0.54
     charité
    -0.51
    dafx
    -0.48
     quelcon
    -0.48
    Hospitals
    -0.48
     financières
    -0.47
    MEDIUM
    -0.47
    POSITIVE LOGITS
    side
    0.60
     AssemblyCulture
    0.60
     nonatomic
    0.58
    AndroidJUnit
    0.57
    ber
    0.57
    bers
    0.56
    ByVersion
    0.56
    stand
    0.54
    ers
    0.54
    er
    0.54
    Activations Density 0.002%

    No Known Activations