© 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. 91704
    Prev
    Next
    INDEX
    Explanations

    desire or wanting

    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
    Referanser
    -0.52
     parha
    -0.47
     actionTypes
    -0.47
    tiéndose
    -0.47
     aján
    -0.46
    議
    -0.44
     guerres
    -0.43
     Weltkrieg
    -0.43
     geloof
    -0.43
     tibi
    -0.42
    POSITIVE LOGITS
    ReusableCell
    0.92
     to
    0.71
    RegressionTest
    0.69
    addPreferredGap
    0.66
    tainty
    0.65
     nakalista
    0.65
     for
    0.63
     mergeFrom
    0.57
    initComponents
    0.57
    asmussen
    0.55
    Activations Density 0.001%

    No Known Activations