© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13932
    Prev
    Next
    INDEX
    Explanations

    decision

    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
    kháu
    -0.55
    Personensuche
    -0.54
    stini
    -0.52
     unknownFields
    -0.51
    aternion
    -0.51
     OnInit
    -0.51
    DockStyle
    -0.51
    posedge
    -0.50
     UnityEditor
    -0.49
    OGND
    -0.47
    POSITIVE LOGITS
     taken
    0.81
    Taken
    0.76
     myſelf
    0.73
     Efq
    0.72
    taken
    0.67
     leaſt
    0.64
     Taken
    0.64
     becauſe
    0.61
     themſelves
    0.59
     leſs
    0.59
    Activations Density 0.009%

    No Known Activations