© 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. 4-CLT-HP
    7. 1201
    Prev
    Next
    INDEX
    Explanations

    the

    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
    BASEPATH
    -0.43
     Tri
    -0.42
     alike
    -0.41
     who
    -0.39
    nius
    -0.39
     den
    -0.38
     means
    -0.36
     Information
    -0.35
     S
    -0.34
     New
    -0.34
    POSITIVE LOGITS
    AndEndTag
    1.02
     חיצוניים
    0.82
    Personendaten
    0.77
     protoimpl
    0.77
     Réponses
    0.77
     الدولى
    0.72
    tableFuture
    0.71
     Drapeau
    0.70
    Jegyzetek
    0.69
     MenuView
    0.69
    Activations Density 0.005%

    No Known Activations